write a research report on chatgpt

Navigation Menu

Search code, repositories, users, issues, pull requests..., provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications You must be signed in to change notification settings

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

ahmetbersoz/chatgpt-prompts-for-academic-writing

Folders and files.

Repository files navigation

✨ NEW UPDATE: Literature Review Generator

A Custom GPT for Literature Review Generator has been released. It efficiently parses PDF files of research publications, extracts key themes, and creates a literature review section for your academic publications.

TRY NOW: https://chat.openai.com/g/g-G3U8pZGwC-literature-review-generator

ChatGPT Prompts for Academic Writing

In this repository, this list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans. Whether you're a student, researcher, or academic professional, these prompts can help you hone your writing abilities and tackle your writing projects with confidence.

Use directly in: chat.openai.com

The list is regularly updated, so you can keep track of new prompts by following this repository.

TIPS: As there is a limit to the number of words that can be used in ChatGPT, you can input your text multiple times using the prompt "Read this [PARAPGRAPH]:" and then run your final prompt "Considering the above text...".

You can also use prompts splitter: chatgpt-prompt-splitter.jjdiaz.dev

BRAINSTORMING

Article sections, title/topic sentence, introduction, literature review.

NOTE: Be careful and double-check article existence. ChatGPT may generate fake references

Methodology

Experiments, future works, improving language, summarization, plan/presentation, working with documents (available only in gpt-4).

Upload a PDF file of a paper then:

Upload a PDF file of your paper then:

Upload PDF files of papers then:

Upload a figure image then:

Contributors 4

Home → Academic Writing → How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

How to Use ChatGPT to Write a Research Paper: Tips and Tricks to Get You Started

Jordan Kruszynski

• January 4, 2024

If you’re an academic, you’ve probably spent a lot of time planning and writing research papers. It’s a fine art, and one that requires a fair amount of skill, precision and preparation. But whether you’re an old master in the field, or a rookie embarking on your first serious research paper, there are tools that can help you to simplify the planning stages and organise your thoughts more effectively.

One of those tools is the (in)famous ChatGPT , and it’s this that we’ll be focusing on in our article. In the right hands, ChatGPT can become a powerful research tool that will make your paper-writing that little bit easier. So sit back, relax, and discover our tips and tricks for using ChatGPT to write a research paper.

What is ChatGPT?

Just in case you don’t already know, ChatGPT is an artificial intelligence tool developed by OpenAI that can help you with your research. It uses natural language processing to understand what you’re looking for and provide you with relevant information. You can ask it questions, and it will provide you with answers in a conversational style, as well as offer sources to back up its information.

One of the biggest advantages of ChatGPT is that it can save you time. Instead of spending hours searching for sources, you can simply ask ChatGPT for help. This can bring you a reliable list of sources for further investigation fairly quickly. It’s crucial to note however that the AI shouldn’t be exploited to do the actual writing of the paper for you. This could see you accused of plagiarism or misconduct, and besides, as a researcher, you’re probably rightfully proud of your ability to write a compelling paper.

Another advantage of ChatGPT is that it’s always available (even when libraries or other sources of information might be inaccessible) so you can work on your research paper at any time of day or night.

Interested in learning more about how AI programs like ChatGPT are changing the academic landscape? Listen to Oxford researcher Samantha-Kaye Johnston’s views from the frontline in this exciting episode of The Research Beat podcast.

The benefits of using ChatGPT to write a research paper

There are many benefits to using ChatGPT for research papers. Firstly, as we mentioned earlier, it can save you time . A slow drag of several hours looking for specific sources can be reduced to just a few minutes with the AI’s help.

Secondly, it can help you find sources that you might not have found otherwise . ChatGPT has access to a wide range of sources, including academic journals and books.

Thirdly, it can help you organise your research . ChatGPT can provide you with a summary of the information you’ve gathered, making it easier to analyse and integrate into your research paper.

How to use ChatGPT to write a research paper – a step by step guide

• Start by creating a list of questions that you want to answer in your research paper.
• Open ChatGPT and ask it one of the questions on your list, for example, ‘What is the critical history of feminist literature in Europe?’
• ChatGPT will provide you with a list of sources to check out.
• Read through the sources and take notes on the information that is relevant to your research question.
• Repeat steps 2-4 for each question on your list.
• Once you’ve gathered all of your information, organise it into an outline for your research paper.
• Use the information you’ve gathered to write your research paper.

Working with your sources

Once you have your sources in order, you might want to use prompts to get help from ChatGPT with other parts of the writing process. A prompt is a specific instruction to the AI that can give you tailored information or responses. For example, if you’re struggling to understand part of another research paper, you could use the following prompt:

‘Please explain the following paragraphs in simple words. I am having trouble understanding (insert concept here).’

Input the prompt along with the relevant passage from the source, and ChatGPT will provide a summary that could help you to unlock your understanding of the tricky concept.

Looking for ChatGPT prompts tailor-made for academics? Check out Audemic’s list of over 50 prompts to help you with your work and research!

Writing tips and tricks for using ChatGPT

When using ChatGPT to write a research paper, it’s important to keep a few things in mind. Firstly, make sure that you’re using reliable sources . ChatGPT can provide you with a list of sources, but it’s up to you to determine which ones are reliable.

Secondly, make sure that you’re paraphrasing the information you’ve gathered in your own words . You don’t want to cheat or be accused of it.

Finally, make sure that you’re using the information you’ve gathered to answer your research questions . Everything you uncover through ChatGPT should be used to feed your own understanding and improve the quality and precision of your answers.

Common mistakes to avoid when using ChatGPT to write a research paper

While ChatGPT is an excellent tool for research papers, there are some common mistakes to avoid:

• Crucially, don’t rely too heavily on ChatGPT. It’s essential to do some of your research on your own and use ChatGPT to supplement it.
• Don’t forget to cite your sources correctly. Just because ChatGPT provided you with the information doesn’t mean that you don’t need to cite it. Moreover, ChatGPT cannot actually produce academic citations for you.
• Always remember to proofread your research paper carefully, especially if you’ve used AI elements to construct it.

ChatGPT vs. traditional research methods

While traditional research methods have their advantages and always will, ChatGPT, as we’ve seen, has some of its own. We think one of the best uses for AI programs like ChatGPT is to accelerate parts of the paper-writing process that would otherwise take hours. If you can use the AI to produce a list of interesting and relevant sources, then you can get to work quickly as an academic, studying and analysing those sources to determine their value within your paper. In general, if you approach ChatGPT with an attitude of maintaining quality and integrity, then it can only enhance your work.

Final Thoughts

ChatGPT is everywhere at the moment, and while it has stirred up a great deal of controversy thanks to its implications for academic integrity, it can be an excellent tool for helping to write research papers . The key is using it correctly, and not relying too heavily on it. Focusing on how it can enhance your already-sharp academic writing skills will allow you to save time, find plenty of valuable sources, and organise your paper’s structure more effectively. And that’s how to use ChatGPT to write a research paper!

ChatGPT is not the only AI tool that can help with these parts of the paper-writing puzzle. If you want to listen to academic papers, break them down into digestible pieces and freely take notes on them, then Audemic is waiting for you. Try it for free today!

Keep striving, researchers! ✨

Table of Contents

Related articles.

How to Publish a Research Paper: A Step-by-Step Guide

You’re in academia. You’re going steady. Your research is going well and you begin to wonder: ‘How exactly do I get a

Behind the Scenes: What Does a Research Assistant Do?

Have you ever wondered what goes on behind the scenes in a research lab? Does it involve acting out the whims of

How to Write a Research Paper Introduction: Hook, Line, and Sinker

Want to know how to write a research paper introduction that dazzles? Struggling to hook your reader in with your opening sentences?

Blog Podcast

Privacy policy Terms of service

Subscribe to our newsletter!

Discover more from Audemic: Access any academic research via audio

Subscribe now to keep reading and get access to the full archive.

Type your email…

Continue reading

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• NATURE PODCAST
• 12 July 2023

ChatGPT can write a paper in an hour — but there are downsides

• Noah Baker ,
• Benjamin Thompson &

You can also search for this author in PubMed   Google Scholar

Hear the latest from the world of science, with Noah Baker, Benjamin Thompson and Dan Fox.

In this episode:

00:23 Using ChatGPT to generate a research paper from scratch

A pair of scientists have produced a research paper in less than an hour with the help of the generative artificial intelligence (AI) ChatGPT. The aim of this exercise was to explore the technology’s ability to act as a research ‘co-pilot’ and spark debate about its use. While AI tools like ChatGPT have the potential to speed up research, it is still unclear what role they should play in research.

Nature News: Scientists used ChatGPT to generate an entire paper from scratch — but is it any good?

06:28 Last week saw the world’s hottest day on record – twice

On Monday last week the average worldwide temperature reached 17.01 °C, beating a record set in 2016. Then, on Tuesday that record was broken again, as average temperatures hit 17.18 °C. Further record-breaking days may follow this year as a result of climate change, and the arrival of the El Niño weather phenomenon, which is expected to strengthen in the coming months.

Bloomberg: Earth Keeps Breaking Temperature Records Due to Global Warming

Nature News: El Niño is here — how bad will it be?

10:03 Anti-ageing protein boosts monkey memories

Injecting monkeys with the naturally occurring protein klotho can improve their cognition. Previous work had shown that elevated levels of the enzyme could improve cognitive functions in mice, now researchers have shown that injecting klotho into old rhesus macaques caused them to perform better in memory-related tasks. While the mechanism behind this effect is unclear, it’s hoped that the finding could ultimately lead to new treatments for neurodegenerative diseases in humans.

Nature News: Anti-ageing protein injection boosts monkeys’ memories

Subscribe to Nature Briefing, an unmissable daily round-up of science news, opinion and analysis free in your inbox every weekday.

Never miss an episode. Subscribe to the Nature Podcast on Apple Podcasts , Google Podcasts , Spotify or your favourite podcast app. An RSS feed for the Nature Podcast is available too.

Benjamin Thompson

Hi, Benjamin from the Nature Podcast here. We're going to change things up a little bit this week. And we're going to take a deep-dive into some stories that have been in the Nature Briefing over the past few days. And joining me to do so are Noah Baker. Noah, how're you doing today?

I'm very well. Thank you. Looking forward to chatting about Briefing items.

And Dan Fox, Dan. Hello.

Hi. How's it going?

Yeah, it's going very, very well. Well, listen, three stories to go through today. Noah, why don't you go first? You're talking about AI? Right?

Yeah. So I think probably one of the hottest topics at the moment is generative AI. And this is a story all about ChatGPT, the poster child of said movement in the news. But specifically, this is about some researchers that have used ChatGPT to generate an entire paper from scratch. And so there's a news article in Nature that I've been reading about whether or not that paper is any good, what the limitations are. Should we be scared? Spoiler alert. No, not really yet. But maybe it could be useful as a tool in the future.

When you say an entire paper, do you mean what abstract, introduction, methods, conclusion? The whole business?

Absolutely the whole thing. So it did the analysis with some prompts. And it created an article that was quote, fluent, insightful and presented in the expected structure for a scientific paper. But it did it with a lot of help. So the researchers wrote a program which prompted ChatGPT to do this in stages. And I can talk you through what those stages were from the sort of beginning of the research all the way through to the published paper in the end, but this entire process took less than an hour, which is I guess, a big part of why this is something that's worthy of talking about now.

Maybe we start off with, with what was this paper about? And how did the researchers go about making it?

Yeah, so it's two researchers from Israel from Technion in Haifa. And they essentially started with the data, right. So they started with some freely available data, CDC telephone survey data about 250,000 people talking about their diabetes status. And then they wrote this program, which essentially prompted ChatGPT in an automated way. So it said, 'Hey, ChatGPT write some code that could uncover patterns in this data'. And so it wrote some code to uncover some patterns. And its first attempt, it was a nightmare. Loads of errors, things that didn't work. But the program took those error messages, fed it back into ChatGPT and said 'do better'. And eventually it did, it produced code that could be used to explore the dataset. And then they said, 'Okay, cool. You've got a structured data set now, look for some things'. And so it said, 'why don't you explore how physical activity and diet are related to diabetes risk', so it generated more code. And it found yep, sure, eating more fruit and vegetables and exercising is linked to a lower risk of diabetes according to these data. And then still via this program, it prompted ChatGPT to summarize those findings in a table, then write the whole results section. Then step-by-step, they got it to write the abstract, the introduction, the methods and the discussion section of the manuscript. And then after that, refine all the text so that it could go through and refine it all. So there was lots and lots of prompts. But what they ended up with is in less than an hour, they've essentially done some research and written a paper, or rather ChatGPT had done some research and written a paper.

I mean, that's really interesting. But I guess diabetes, and correlation with eating fruit and veg and physical activity is not the most, not the most novel piece of research.

Yeah, for sure. I mean, this is one of the things that the researchers quoted in this story have said, you know, this is not something that's going to surprise any medical expert. It's not close to being novel. But really importantly, one of the things that ChatGPT did do when it was generating the text for this paper is it used quotes like this "addresses a gap in the literature", which this very much isn't. There's very little novel about this finding, in terms of our understanding of diabetes and risk factors for diabetes. And this is one of the big concerns that scientists have about using ChatGPT for this kind of purpose.

So it's not necessarily what it found then. But it's the fact that it could be done that that is so interesting about this work.

Yeah. I mean, researchers are trying to find ways that ChatGPT could be used as a tool, essentially, it's like, how could it help the scientific process? How could it be used to make things more efficient for researchers to be able to do more work, more insightful work, see things that perhaps aren't seen otherwise? But there are lots and lots of questions around whether or not you can do that. This approach of trying to get it to create an entire paper means that you end up with a paper that's not super novel or exciting, and equally has lots of made up citations. It's another thing that it did, it hallucinated concepts it didn't really understand, well, because ChatGPT doesn't understand anything, it doesn't really understand any of that context. And so it needs a lot of support from the researchers, however, a lot happened in an hour. So there's a discussion in this piece about how it might be useful and where the problems might lie. And there are suggestions that it could be very useful to just throw up a bunch of potential avenues for research, or perhaps things like summarization of results could be something that ChatGPT could do very quickly. Or perhaps even things like writing code is something that ChatGPT can do very quickly. So there are places it could be useful, but building an entire paper, perhaps not. And there are other reasons that this could be concerning. So one of the things that's that's mentioned here in this story is things like P-hacking. So P-hacking is when scientists just test a bunch of hypotheses on datasets, hoping that one of them's going to work and then they just only talk about that thing. And in a world where you can essentially say, 'Hey, ChatGPT, do some P-hacking for me' because it can look at so many things so quickly, then potentially you end up with a situation where you're using an AI to enhance this relatively dishonest practice. So concerns abound, but potentially a very powerful tool. There's just a lot of kinks to work out before we can really get there and use it appropriately. And that includes in publishing research as well.

Yeah, I mean, quite the quite the sort of two-way street and for a number of reasons, right, because you said you could do it in an hour. And I can almost hear some of the researchers listening to this podcast, rubbing their hands going 'writing papers is boring and takes ages, this will be super useful'. But the other side of that is, it could be used to just churn out absolute dross, right. And these kind of, we've heard about paper mills before publishing fake research.

Yeah, absolutely. And I think there's a lot to be watched here, you know, there's a lot of onus on journals like Nature and other journals to continue to develop their process for how AI use can be declared. I mean, this is something that is very important to try to declare how AI tools are used in papers so that we can better see and spot places where there may have been biases or hallucinations, inputted by the generative AI. And that's something that editors can do. It's something that scientists need to do, because the stuff that's created can be so fluent ChatGPT can make stuff that sounds so convincing, that even experts in the field can sometimes struggle to see places where it's made stuff up, or it's seen things that aren't there. So, lots to watch, but perhaps smaller steps at the moment, so we can make things actually useful.

Well, I have a feeling that isn't the last we're going to hear about ChatGPT on the Nature Podcast . But let's move on to our second story today. And it's a story that I've brought, and I read about it in Bloomberg . And it's about some records that have been broken, but sadly, not in a good way. It's how data suggests that last week, the average global temperatures across the world broke the existing record, not once but twice.

Yeah, this is the record in like human history, right, a really significant record to break twice in one year.

Yeah it's not a good one. And this is according to data from the US National Centers for Environmental Prediction. In terms of the numbers then, the average worldwide temperature reached 17.01 ° on Monday last week. And that was then shortly broken on Tuesday, when they reached 17.18 °C. This record isn't official, it has to be said. But I think it is quite a sobering indication of where things are right now.

Yeah, I mean, point two-degree rise doesn't seem much on any given day. But across, you know, when you start to bring in averages, and also when you start to think about this as a global temperature, it's a really significant jump in temperature. Right?

Absolutely. And this comes against a backdrop of a lot that's going on across the world right now. I mean, there's been huge heatwaves in China with records are broken there. The hottest June in the UK on record, Antarctica had its highest temperature recorded in July, at 8.7 °C, heatwaves in Spain, you know, across the land and sea.

So is there a sense of some of the reasons behind it being the hottest day on record sort of two, two days in a week?

WellI mean, you'll be you'll be shocked to know that climate change is clearly playing a part in the fact that the world is warming. But there's something else involved here as well, and that is El Niño, which is this sort of global weather phenomenon that happens every sort of two to seven years.

Right, So we have a record broken twice in one week. And then at the same time, we have a new El Niño cycle starting, which we know is associated with particularly high temperatures. This doesn't sound like good maths, is this gonna be a particularly big El Niño cycle?

Well, that's a great question. And it's actually yet to be decided. Researchers don't quite know yet. But what I can say is last time, there was a strong El Niño that corresponded to the hottest year on record, and that was in 2016. So from what I've read, there is a sense that really, maybe 2023, or maybe even 2024, when El Niño really kicks in, could break the record for the for the hottest year.

And with hot temperatures also comes more extreme weather and loads of other potential knock ons, right?

So this changes weather patterns across the globe, due to a slackening of the trade winds above the tropical Pacific Ocean. It could lead to droughts in Australia and southeast Asia, increased rainfall in places like the Horn of Africa. And that can lead to localized flooding, which can damage crops. But also other things as well, which maybe not entirely obvious. For example, strong rainfall could lead to an increase in the number of mosquitoes, which could then lead to more diseases being spread. Something similar was seen in Peru, weather pattern change was linked to a severe outbreak of the disease, dengue, which of course, is a viral disease spread by mosquitoes. So there's a great deal going on here, which could have really quite severe effects on life and livelihoods. And of course, you know, in the face of a warming world, one of the only ways we can get on top of this is reducing emissions, right. And of course, COP28 is coming up in November. And it'd be interesting to see in the face of of what is potentially going to happen, whether that will affect negotiations and discussions at that meeting at all.

I wonder whether or not this will change the urgency with which people discuss things. Anyway. Dan, do you have anything a little bit more uplifting? Perhaps maybe something a little bit less doom-and-gloom to talk about as a final story for the show.

Yeah. So this is I think it's quite a positive research development. So some researchers have published a paper that's come out in Nature Aging , where rhesus macaques were injected with a protein called klotho. And that increased their cognitive ability, quite significantly, for well over two weeks, and is potentially a treatment for degenerative diseases like Alzheimer's and Parkinson's and dementia.

So, I know this is probably trivializing, but it sounds to me like scientists have injected monkeys with a super smart-serum.

I mean, it's very much the plot of 2011's Rise of the Planet of the Apes , starring James Franco. But this is a bit more exciting in that...

But I mean, it's probably less exciting. There's no talking monkeys. But they are they are 15% better at finding snacks.

I was interested in that. So what is it that they've actually done to measure cognitive ability here? Is this a series of behavioral tasks?

So the tests the researchers used, involved putting a treat reward into one of a variety of different wells, so different sort of geographical location, spatial locations. That experiment was hidden from the monkeys for a period of time. And then when they returned, they had to find the treat that they'd seen hidden previously. So the researchers say, this is similar to a task like finding your car in a busy car park, and it's something that specifically gets harder as you get older. So the rhesus macaques were older macaques as well. So the average age of these monkeys was around 22 years old, which the authors of the paper say corresponds to being about a 65 year old human. And before they were injected with this protein, they successfully found the treat in the correct well 45% of the time,after an injection with this protein klotho, they found that 60% of the time. So a 15%, increase in their ability to find their car in a car park, find their their tasty snack, and that lasted for two weeks.

Klotho that is a protein, I have to say, I've never heard of. What is klotho, and what's the scientists know about it?

So klotho is protein that's expressed in the body in a few different places, it comes in a few different varieties. And these researchers are looking at alpha klotho. So it's something that actually decreases in the body as you age. And the researchers have called it a 'longevity factor'.

Hence it becoming a target to try to understand what's going on with aging, because it's something that seems to be correlated with aging.

Wow, what was going on in the brains of these monkeys then? Because it seems like fairly straightforward to inject them with protein, but I'm sure there's more to it than that.

Well, I think that's one of the fascinating parts of the story is they don't really know. The actual mechanics of how this protein is working, is not very well understood. So it's previously been shown that they get a similar effect from injecting this protein into mice, increases in synaptic plasticity and cognition and in resilience against aging and Alzheimer's and Parkinson's disease. But they also know that this protein doesn't pass the blood-brain barrier. So there's some sort of intermediary that's communicating this effect into the brain. And that isn't well understood. And something else that complicates matters, and shows that there's kind of a more complicated process going on then the researchers initially thought is that, while a low-dose works very well, and gives this two-week effect, at higher doses, there's no cognitive improvement. And they think that possibly even higher doses, there'd be cognitive impairment. So it's not really clear exactly what's going on inside the body.

Well, so you can improve a monkey memory using a protein without really understanding how the protein works. Could you improve a human memory by doing a similar thing?

The short answer is, is yes. So it's already been shown that individuals that have elevated klotho levels due to natural variation show improved cognition and decreased risk of dementia and Alzheimer's. So there's already been a demonstrated benefit to klotho in humans. And the researchers behind this work have said that there's a very strong reason to jump into human clinical trials now.

So lots of excitement in the field. But knowing scientists as I do, I can imagine there are certainly people that are saying, Sure, clinical trials will be interesting. But we do really need to understand this mechanism a little bit better, right?

Absolutely. And there are research saying that a better understanding of the proteins mode of action will be crucial for realizing its clinical potential and the authors of the paper, and the authors also mentioned in the paper, that identifying these intermediaries that are taking the message from this klotho across the blood-brain barrier into the brain itself, is going to be key.

When they do work out what's going on with that intermediary, please come back on and let us know. But let's leave it there for this week's Briefing Chat and listeners, for more of these stories, look out for links in the show notes, where you'll also find a link where you can sign up for the Nature Briefing to get even more science stories like this delivered directly to your inbox. But for this week, all that's left to say is Noah and Dan, thank you so much for joining me.

Cheers, Ben.

Yeah, thanks for having me.

doi: https://doi.org/10.1038/d41586-023-02298-x

Related Articles

• Climate change
• Climate sciences

Western scientists more likely to get rejected papers published — and do it faster

News 02 JUL 24

Spy on millions of sleeping butterflies and more — June’s best science images

‘It can feel like there’s no way out’ — political scientists face pushback on their work

News Feature 19 JUN 24

Elite researchers in China say they had ‘no choice’ but to commit misconduct

News 11 JUN 24

Chinese research collaborations shift to the Belt and Road

Nature Index 05 JUN 24

Japan’s push to make all research open access is taking shape

News 30 MAY 24

Last year’s summer was the warmest in 2,000 years

News & Views 03 JUL 24

Climate change is worsening the housing crisis — we must tackle the two together

World View 02 JUL 24

Deep-sea dye confirms turbulent-mixing theory — with implications for climate

News & Views 26 JUN 24

Postdoctoral Research Scientist: DNA Replication and Repair in Haematopoietic Stem Cells

An exciting opportunity has arisen for a highly motivated Postdoctoral Research Scientist to join Professor Chapman’s Group, to investigate how DNA...

Oxford, Oxfordshire

University of Oxford, Radcliffe Department of Medicine

Tenure-Track Assistant Professor to the rank of Associate Professor in computational biology

UNIL is a leading international teaching and research institution, with over 5,000 employees and 15,500 students split between its Dorigny campus, ...

Lausanne, Canton of Vaud (CH)

University of Lausanne (UNIL)

Post-doctoral researcher (m/f/d) in Marine Microbial Natural Product Chemistry

GEOMAR Helmholtz Centre for Ocean Research Kiel, Wischhofstraße 1-3, 24148 Kiel, Germany

Helmholtz Centre for Ocean Research Kiel (GEOMAR)

Global Faculty Recruitment of School of Life Sciences, Tsinghua University

The School of Life Sciences at Tsinghua University invites applications for tenure-track or tenured faculty positions at all ranks (Assistant/Ass...

Beijing, China

Tsinghua University (The School of Life Sciences)

Sales Executive, Nature Careers

If you're customer-focused, thrive in sales, and want to impact Europe's job market, join our Nature Careers team !

London - hybrid working model

Springer Nature Ltd

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Have a language expert improve your writing

Check your paper for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• How to Write an Essay with ChatGPT | Tips & Examples

How to Write an Essay with ChatGPT | Tips & Examples

Published on June 22, 2023 by Koen Driessen . Revised on November 16, 2023.

Passing off AI-generated text as your own work is widely considered plagiarism. However, when used correctly, AI tools like ChatGPT can legitimately help guide your writing process.

These tools are especially helpful in the preparation and revision stages of your essay writing.

You can use ChatGPT to:

• Write a research question
• Develop an outline
• Find relevant source information
• Summarize or paraphrase text
• Get feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Writing a research question, developing an outline, finding source recommendations, summarizing/paraphrasing text, getting feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to brainstorm potential research questions or to narrow down your thesis statement . Begin by inputting a description of the research topic or assigned question. Then include a prompt like “Write 3 possible research questions on this topic.”

You can make the prompt as specific as you like. For example, you can include the writing level (e.g., high school essay, college essay), perspective (e.g., first person) and the type of essay you intend to write (e.g., argumentative , descriptive , expository , or narrative ).

You can also mention any facts or viewpoints you’ve gathered that should be incorporated into the output.

If the output doesn’t suit your topic, you can click “Regenerate response” to have the tool generate a new response. You can do this as many times as you like, and you can try making your prompt more specific if you struggle to get the results you want.

Example: Using ChatGPT to write a research question

• Generate three possible research questions for an argumentative high school essay on the following topic: “The long-term impact of the Covid-19 pandemic.”
• To what extent has the Covid-19 pandemic exacerbated existing social inequalities and what measures can be taken to address these disparities in the long term?
• How has the Covid-19 pandemic transformed education systems, and what are the potential long-term implications for students’ learning outcomes and educational equity?
• What lessons can be learned from the Covid-19 pandemic to enhance global preparedness and response to future public health crises, and how can these lessons be effectively implemented in the long term?
• Based on the second question, develop three further research questions with a specific focus on distance learning.
• What are the long-term effects of widespread adoption of distance learning during the Covid-19 pandemic on students’ academic performance, motivation, and overall educational outcomes?
• How has the shift to distance learning impacted the social and emotional well-being of students, and what strategies can be implemented to address any negative consequences in the long term?
• What are the key factors that contribute to the success of distance learning programs, and how can educational institutions and policymakers ensure equitable access to quality education in the long term, especially for marginalized and underserved student populations?

Don't submit your assignments before you do this

The academic proofreading tool has been trained on 1000s of academic texts. Making it the most accurate and reliable proofreading tool for students. Free citation check included.

Try for free

Once you’ve decided on a research question, you can use ChatGPT to develop an essay outline . This can help keep you on track by giving you a clear idea of what topics you want to discuss and in what order.

Do this by prompting ChatGPT to create an outline for a specific research question, mentioning any topics or points you want to discuss. You can also mention the writing level and the intended length of your essay so that the tool generates an appropriate outline.

You can then refine this by further prompting ChatGPT or editing the outline manually until it meets your requirements.

Examples: Using ChatGPT to generate an essay outline

• Develop an outline for an argumentative high school essay with the following research question: “What are the long-term effects of widespread adoption of distance learning during the Covid-19 pandemic on students’ academic performance and overall educational outcomes?”The essay will be about 4 pages long.
• Background information on the Covid-19 pandemic and the shift to distance learning
• Thesis statement: The widespread adoption of distance learning during the Covid-19 pandemic has had both positive and negative long-term effects on students’ academic performance and overall educational outcomes.
• Increased flexibility and personalized learning opportunities
• Access to a wider range of resources and educational materials
• Development of self-directed learning skills
• Critiques and limitations of previous studies
• Lack of face-to-face interaction and reduced social engagement
• Increased potential for distractions and lack of structure
• Technological barriers and unequal access to resources
• Examination of studies and data on academic achievement during distance learning
• Analysis of long-term effects on educational attainment and future opportunities
• Discussion of potential implications for college admissions and career readiness
• Strategies for promoting student engagement and motivation in distance learning
• Importance of teacher-student communication and support
• Addressing technological disparities and ensuring equitable access to resources
• Recap of the main points discussed
• Emphasize the need for further research and long-term planning to optimize distance learning experiences
• Restate the thesis and provide a final thought on the potential long-term effects of distance learning on students’ academic performance and overall educational outcomes

Once you know the scope of your essay, you can find relevant primary and secondary sources to support your argument.

However, we don’t recommend prompting ChatGPT to generate a list of sources as it occasionally makes mistakes (like listing nonexistent sources). Instead, it’s a good idea to use ChatGPT to get suggestions for the types of sources relevant to your essay and track them down using a credible research database or your institution’s library.

When you have found relevant sources, use a specialized tool like the Scribbr Citation Generator to cite them in your essay.

Example: Using ChatGPT to find sources

• What types of sources can I use to write an essay on the following research question?”What are the long-term effects of widespread adoption of distance learning during the Covid-19 pandemic on students’ academic performance and overall educational outcomes?”
• Academic Journals and Research Articles: Look for scholarly articles and research studies published in peer-reviewed academic journals. These sources often provide in-depth analysis, empirical evidence, and statistical data on the long-term effects of distance learning.
• Educational and Government Reports: Reports published by educational institutions, government agencies, or educational organizations can offer valuable insights into the impact of distance learning on academic performance and educational outcomes. These reports may include surveys, case studies, and data analysis specific to the Covid-19 pandemic and distance learning.
• Official Websites and Publications: Explore the official websites of educational institutions, education ministries, or educational technology companies. They often publish articles, white papers, or research findings related to distance learning and its effects on students’ academic performance.
• Expert Interviews or Opinion Pieces: Seek out interviews or opinion pieces from experts in the field of education, distance learning, or pedagogy. These sources can provide valuable perspectives and insights on the long-term effects of distance learning on students’ educational outcomes.
• Online Databases and Digital Libraries: Utilize online databases and digital libraries such as JSTOR, Google Scholar, or academic databases provided by your educational institution. These platforms offer a wide range of scholarly articles, research papers, and publications that can support your arguments.
• Surveys and Studies Conducted by Educational Institutions: Some schools or universities may have conducted their own surveys or studies to evaluate the impact of distance learning on students. Check if your educational institution has published any research findings or survey results that are relevant to your topic.

During your writing process, you can use ChatGPT as a summarizing tool to condense text to its essential ideas or as a paraphraser to rephrase text in clear, accessible language. Using ChatGPT in these ways can help you to understand complex material, express your own ideas more clearly, and avoid repetition.

Simply input the relevant text and prompt the tool to summarize or paraphrase it. Alternatively, you can use Scribbr’s free text summarizer and Scribbr’s free paraphrasing tool , which are specifically designed for these purposes.

Example: Using ChatGPT to summarize/paraphrase

• Paraphrase the following text using clear language:”Engaging in an extensive examination of the intricate interplay between remote instructional methods and academic achievement necessitates consideration of diverse factors, including the pedagogical efficacy of virtual platforms, the socioemotional ramifications of reduced face-to-face interactions, the equitable accessibility of technological resources, and the potential long-lasting implications for students’ educational trajectories and future opportunities.”
• To thoroughly explore the connection between remote teaching methods and academic success, it is crucial to take into account various factors. These factors include evaluating how well virtual platforms support effective teaching, understanding the impact of limited in-person interactions on students’ emotional well-being, ensuring fair access to technology resources, and recognizing the potential long-term effects on students’ educational paths and future prospects.

Check for common mistakes

Use the best grammar checker available to check for common mistakes in your text.

Fix mistakes for free

Once you’ve written your essay, you can prompt ChatGPT to provide feedback and recommend improvements.

You can indicate how the tool should provide feedback (e.g., “Act like a university professor examining papers”) and include the specific points you want to receive feedback on (e.g., consistency of tone, clarity of argument, appropriateness of evidence).

While this is not an adequate substitute for an experienced academic supervisor, it can help you with quick preliminary feedback.

You can also use ChatGPT to check grammar mistakes. However, ChatGPT sometimes misses errors and on rare occasions may even introduce new grammatical mistakes. We suggest using a tool like Scribbr’s free grammar checker , which is designed specifically for this purpose. Or, for more in-depth feedback, try Scribbr’s proofreading and editing service .

Example: Using ChatGPT for feedback

• Feedback the above text with regard to consistency of tone, clarity of argument, appropriateness of evidence, and coherence of structure.
• Clarity of Argument: The argument could be further clarified by explicitly connecting the discussed factors to their impact on academic performance. For example, explicitly stating how the proficiency of virtual platforms and equitable access to technology affect academic performance would strengthen the clarity of the argument.
• Appropriateness of Evidence: The evidence provided is generally appropriate and relevant. To enhance the strength of the evidence, consider incorporating specific examples, research studies, or statistics that directly support the discussed factors and their impact on academic performance. This would provide stronger evidence for the claims made.
• Coherence of Structure: The structure of the text is coherent, with a clear introduction, body paragraphs addressing different factors, and a conclusion. To improve coherence, consider adding transitional phrases or sentences at the beginning or end of paragraphs to facilitate the smooth flow of ideas between paragraphs. This would enhance the overall structure and make it easier for the reader to follow the argument.

Overall, the text demonstrates a consistent tone, a clear argument, appropriate evidence, and a coherent structure. Clarifying the argument by explicitly connecting the factors to their impact, incorporating stronger evidence, and adding transitional phrases for better coherence would further enhance the text’s effectiveness. Note Passing off AI-generated text as your own work is generally considered plagiarism (or at least academic dishonesty ) and may result in an automatic fail and other negative consequences . An AI detector may be used to detect this offense.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarize text . This can help you understand complex information more easily, summarize the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summarizer , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialized tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, it’s not a good idea to do so in general—first, because it’s normally considered plagiarism or academic dishonesty to represent someone else’s work as your own (even if that “someone” is an AI language model). Even if you cite ChatGPT , you’ll still be penalized unless this is specifically allowed by your university . Institutions may use AI detectors to enforce these rules.

Second, ChatGPT can recombine existing texts, but it cannot really generate new knowledge. And it lacks specialist knowledge of academic topics. Therefore, it is not possible to obtain original research results, and the text produced may contain factual errors.

However, you can usually still use ChatGPT for assignments in other ways, as a source of inspiration and feedback.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

Driessen, K. (2023, November 16). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved July 4, 2024, from https://www.scribbr.com/ai-tools/chatgpt-essay/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, how to use chatgpt in your studies, what are the limitations of chatgpt.

Koen Driessen (Scribbr Team)

Thanks for reading! Hope you found this article helpful. If anything is still unclear, or if you didn’t find what you were looking for here, leave a comment and we’ll see if we can help.

Still have questions?

"i thought ai proofreading was useless but..".

I've been using Scribbr for years now and I know it's a service that won't disappoint. It does a good job spotting mistakes”

SYSTEMATIC REVIEW article

Exploring the impact of chatgpt: conversational ai in education.

• 1 Information Technology Center, University of Sharjah, Sharjah, United Arab Emirates
• 2 Department of Computer Science, University of Sharjah, Sharjah, United Arab Emirates

Artificial intelligence integration, specifically ChatGPT, is becoming increasingly popular in educational contexts. This research paper provides a systematic literature review that examines the effects of incorporating ChatGPT into education. The study examines four primary research questions: the benefits and challenges of ChatGPT, its impact on student engagement and learning outcomes, ethical considerations and safeguards, and the effects on educators and teachers, based on an analysis of numerous scientific research articles published between 2022 and 2023. The results emphasize the numerous benefits of ChatGPT, such as the opportunity for students to investigate AI technology, personalized assistance, and improved learning experiences. Furthermore, advantages such as enhanced learning and enhanced information accessibility are identified. Nevertheless, ethical considerations and biases in AI models are also highlighted. ChatGPT enhances student engagement by offering personalized responses, prompt feedback, and rapid access to information, resulting in enhanced learning outcomes and the growth of critical thinking abilities. Ethical considerations and safeguards, including user education, privacy protection, human supervision, and stated guidelines, are essential for responsible use. The integration of ChatGPT transforms the role of educators from content delivery to assistance and guidance, thereby fostering personalized and differentiated learning. Educators have to consider ethical considerations while monitoring student usage in order to facilitate this transformation. Educational institutions can increase student engagement, learning outcomes, and the responsible use of AI in education by addressing challenges, establishing ethical guidelines, and leveraging the strengths of ChatGPT. This will prepare students for future challenges.

1 Introduction

In the rapidly evolving landscape of artificial intelligence, ChatGPT, a cutting-edge language model developed by OpenAI, has emerged as a trailblazing innovation, captivating the attention of researchers and practitioners alike. This research paper delves into the transformative potential of ChatGPT, exploring its remarkable advancements and impact across various domains ( Aljanabi and ChatGPT, 2023 ; Thorp, 2023 ). The journey begins with integrating ChatGPT with other AI technologies, such as computer vision and robotics. ChatGPT propels human-computer interactions to new heights by synergizing these cutting-edge advancements, offering unparalleled personalization and intuitive experiences. As users engage with ChatGPT, its ability to learn from individual preferences empowers the creation of tailored responses, revolutionizing the way humans interact with AI systems ( Aljanabi and ChatGPT, 2023 ). Within the realm of education, ChatGPT’s potential to enhance learning experiences takes center stage. This powerful language model fosters dynamic and evolving learning environments by transcending traditional search engine constraints. Students are encouraged to actively participate in interactive sessions actively, promoting deep engagement and reflective thinking. Drawing on its powerful Generative Pre-trained Transformer (GPT-3), ChatGPT analyzes vast amounts of data, providing personalized and relatable responses while seamlessly integrating new knowledge through follow-up question responses. This unique feature opens exciting opportunities for educators to adopt innovative teaching methods and create a more interactive and enriching classroom experience ( Ollivier et al., 2023 ).

ChatGPT’s adaptive capabilities enable a more student-centric approach to pursuing personalized learning. Educators can tailor content and teaching methodologies to meet individual needs by analyzing a student’s progress and preferences. This not only empowers students to take ownership of their learning journey but also enhances their motivation and overall academic performance. Furthermore, the AI-powered model’s capacity to adapt to learners’ abilities fosters inclusive education, accommodating diverse learning styles and needs and bridging the gap between educators and students with various backgrounds and skills ( Ollivier et al., 2023 ; Pericles ‘asher’ Rospigliosi, 2023 ). However, the integration of AI in education also demands careful ethical considerations. Ensuring responsible data privacy management is paramount, as educational institutions handle sensitive information about students. Transparent communication with students and their parents regarding the use of AI technologies is essential to build trust and address any concerns related to data security. Additionally, educators must be vigilant about potential biases in AI-generated content, as these models are trained on vast datasets that may inadvertently perpetuate stereotypes or cultural preferences. By actively monitoring and addressing these issues, educators can ensure that ChatGPT is a supportive tool for fostering an inclusive and ethical learning environment ( Kasneci et al., 2023 ). The research paper further explores ChatGPT’s potential in reshaping academic writing, focusing on fields like healthcare, medical education, biomedical research, and scientific writing. As AI language models generate human-like text, they hold immense promise in streamlining content creation and organizing complex information into cohesive manuscripts. The AI-powered model’s ability to assist researchers in drafting, summarizing, and conducting literature reviews simplify the writing process, allowing scientists to focus on the more critical aspects of their research ( Bin Arif et al., 2023 ).

Nevertheless, concerns surrounding the accuracy and integrity of AI-generated scientific writing underscore the need for robust fact-checking and verification processes to uphold academic credibility. The reliance on AI-generated content in scientific literature raises questions about the potential for misinformation and the need to establish mechanisms for transparently identifying and attributing AI-generated contributions in academic publications. Researchers and publishers must work together to ensure rigorous standards for fact-checking and validation when incorporating AI-generated content into scientific papers, safeguarding the quality and reliability of scholarly work ( Alkaissi and McFarlane, 2023 ). Moreover, the paper delves into the critical investigation of using ChatGPT to detect implicit hateful speech. By employing this AI language model to elicit natural language explanations, researchers evaluate its proficiency and compare responses with human-labeled data—shedding light on its potential contributions to address societal issues like hate speech online. However, the study also underscores the importance of exercising caution when utilizing ChatGPT as a data annotation tool, emphasizing the need for responsible application to prevent potential misinformation ( DiGiorgio and Ehrenfeld, 2023 ; Fijačko et al., 2023 ).

In conclusion, the introduction sets the stage for a comprehensive exploration of ChatGPT’s multifaceted impacts, spanning human-computer interactions, educational advancements, and societal challenges. As we embark on this journey, we advocate for the responsible and thoughtful deployment of ChatGPT, recognizing its vast potential while upholding ethical considerations ( DiGiorgio and Ehrenfeld, 2023 ) to ensure a positive and equitable integration of AI language models in diverse applications. By leveraging ChatGPT’s capabilities responsibly, we can unlock a new era of personalized and transformative human-AI interactions, ushering in innovative educational practices and advancing society.

The rest of the paper follows this structure: In Section 2, there is a comprehensive review of literature surveys. Moving on to Section 3, the research’s approach and technique are outlined. Section 4 is dedicated to discussing the findings and outcomes of this review. Finally, Section 5 presents concluding insights and offers recommendations for future research.

2 Literature review

The potential of conversational AI, in particular ChatGPT, to impact the field of education by influencing how students learn and interact with educational content has attracted increasing attention in recent years. The author Ray (2023) presented a comprehensive review of ChatGPT. The study focuses on ChatGPT’s history, technological advancements, and industrial uses. It discusses solutions while addressing ethical challenges, data biases, and safety concerns. The review anticipates what ChatGPT will look like in the future, highlighting improvements in human-AI interaction and research developments. Focusing on teaching and learning, Kohnke et al. (2023) analyze ChatGPT’s use in language teaching and learning in their study. The researchers look into the advantages of using ChatGPT, a generative AI chatbot, in language learning. Additionally, they go over the various arguments and ChatGPT’s drawbacks. As a final point, the study emphasizes the crucial digital skills that instructors and students must have to use this chatbot to improve language learning in an ethical and efficient manner. Another study was undertaken by Baidoo-Anu and Owusu Ansah (2023) to examine ChatGPT’s potential for facilitating teaching and learning. The advantages of ChatGPT, such as personalized and interactive learning, creating prompts for formative assessments, and delivering continuous feedback, are highlighted in their recent work evaluation. However, there are also acknowledged drawbacks, such as the potential for producing inaccurate information, biases in data training, and privacy issues. The paper makes suggestions for utilizing ChatGPT to improve education. Collaboration between policymakers, researchers, educators, and technological professionals is encouraged to ensure the safe and beneficial use of generative AI technologies for enhanced learning experiences.

A thorough paper on ChatGPT is presented by Dwivedi et al. (2023) , which includes 43 contributions from specialists across various disciplines. They acknowledge that ChatGPT can increase efficiency in the banking, hospitality, and IT sectors. However, concerns include practice disruptions, privacy and security hazards, biases, and false information. According to the paper, research is needed in knowledge, ethics, transparency, digital transformation, education, and learning. The handling of generative AI, biases in training data, appropriate implementation contexts, ideal human-AI collaboration, text accuracy assessment, and ethical and legal issues all need further study. Highlights include concerns about biases, dated data, the need for protective policies, and transformational effects on employment, teaching, and learning.

Education plays a vital role in using ChatGPT, and numerous reviews have focused on its educational impact. For instance, Lo (2023) rapidly reviews ChatGPT’s implications for education. The study indicates variable performance levels of ChatGPT across diverse subject categories, ranging from superb to unsatisfactory, by examining 50 publications from useful databases and Google Scholar. The author highlights the difficulties of using ChatGPT as a virtual tutor and instructor assistant. In educational institutions, it is essential to update institutional policies and assessment procedures promptly. To address the effects of ChatGPT on education, it is also crucial to offer instructor training and student instructions. Sok and Heng (2023) address the educational aspect of ChatGPT in their study as they look at the benefits and drawbacks of utilizing ChatGPT in research and education. The study identifies five key advantages of ChatGPT, including developing learning assessments, improving pedagogical practices, providing virtual one-on-one tutoring, facilitating idea formation, and outlining. Academic integrity threats, unfair learning assessments, erroneous information dangers, and risks associated with an overreliance on AI are also presented. The study’s conclusion includes a set of recommendations for using ChatGPT in educational and research contexts. Kasneci et al. (2023) focus on the advancements of large language models in AI, specifically focusing on their educational applications. The authors explore the benefits and challenges of using large language models in education, considering the perspectives of both students and teachers. They highlight current research and applications of these models in educational settings. The study delves into the opportunities and challenges these models present for students and instructors. Additionally, the review discusses the potential of these educational technologies, along with the associated challenges, risks, and strategies for mitigation.

Healthcare education holds a pivotal position within any educational system. Therefore, Sallam (2023) has systematically analyzed the prospective views and legitimate concerns regarding using ChatGPT in healthcare education. The author thoroughly analyzes ChatGPT’s application in healthcare education, considering both optimistic perspectives and legitimate concerns. Based on a comprehensive analysis of 70 research publications, the author investigates the utility of large language models in healthcare teaching, research, and practice. According to the review, ChatGPT offers several benefits, including improving research equity and variety, improving scientific writing, facilitating healthcare research and training, and encouraging individualized learning and critical thinking in healthcare education. According to the author, ChatGPT’s promising uses could lead to paradigm shifts in medical practice, study, and training. Embrace this AI chatbot, nevertheless, is suggested with care given its existing limits.

The related research studies that explore ChatGPT in the field of education are listed in Table 1 . Our study, on the other hand, aims to add to the body of knowledge by thoroughly examining the effects of ChatGPT, an AI conversation tool, on education. We aim to give educators, academics, and policymakers valuable insights into the implications of implementing ChatGPT and conversational AI technologies in educational contexts by reviewing literature, reviews, and technical articles. Ultimately, our research intends to support creative and student-centered teaching and learning techniques while facilitating the successful integration of ChatGPT into education. Stakeholders may make intelligent decisions about ChatGPT’s deployment and use it to improve educational experiences by knowing its benefits, challenges, and ethical issues. However, in our work, we take a thorough approach to using ChatGPT in education. We do not just discuss biases, outdated data, transparency, and legitimacy; we work to fix them. Our research also focuses on the ethical side, ensuring data privacy, inclusivity, and a good balance between AI and human interaction. We explore the benefits and challenges of ChatGPT in education, giving a clear picture of its potential while being cautious about its risks. We aim to lead the way in responsibly using language models for education, setting our work apart from others in this field.

Table 1 . Related work summary.

3 Methodology

The Research survey study in this paper adopts Kitchenham and Charters’ Systematic Literature Review (SLR) approach ( Kitchenham and Charters, 2007 ; Hopkins et al., 2023 ), which consists of three phases: planning, conducting, and reporting, each comprising multiple stages. The planning phase focuses on the review methodology. It encompasses six steps: defining research objectives, devising a search strategy, determining study selection processes, establishing quality evaluation guidelines, outlining the data extraction technique, and synthesizing the collected data. Figure 1 provides a visual representation of these stages.

Figure 1 . The stages of performing systematic literature review.

To refine our research focus, we initially defined our objectives and formulated research questions accordingly. The search strategy involved identifying appropriate search terms that would facilitate the identification of relevant articles related to our investigation. The research methodology employed in this study is illustrated in Figure 2 , which presents the resources we searched from and the selection of the paper procedure. Additionally, Figure 3 explains how many papers appear for each keyword in the search phase and the keyword AI the most found.

Figure 2 . Applied research methodology.

Figure 3 . Keywords utilized in the searching phase.

Moreover, this research survey study aligns with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to ensure transparency and methodological rigor in reporting the systematic literature review process. A PRISMA flow diagram ( Figure 4 ) is provided to illustrate the study selection process, detailing the number of records identified, screened, assessed for eligibility, and included in the review, along with reasons for exclusions at each stage.

Figure 4 . PRISMA flow diagram.

In this paper, thematic analysis was applied to derive insights from the collected data. Thematic analysis is a widely used qualitative method for identifying, analyzing, and reporting patterns (themes) within data. In this study, thematic analysis was implemented following the steps outlined by Braun and Clarke ( Salvagno et al., 2023 ). These steps include:

1. Familiarization with the data: all collected data, including extracted information from selected papers, were thoroughly reviewed to gain familiarity with the content.

2. Generating initial scratches: initial scratches were created to identify interesting features or patterns within the data relevant to the research objectives.

3. Searching for themes: scratches were then organized into potential themes, which represent patterns of meaning across the dataset.

4. Reviewing themes: themes were reviewed to ensure they accurately represent the data and align with the research objectives.

5. Defining and naming themes: each theme was defined and given a clear name (benefits, challenges, ethical…etc.) that succinctly captures its essence.

6. Finalizing the analysis: the final thematic map was created, documenting the relationships between themes and providing a comprehensive overview of the findings.

3.1 Research questions

We aim to investigate the perceived benefits and challenges of using ChatGPT as a conversational AI tool in educational settings. We will explore how ChatGPT influences student engagement and learning outcomes in education. Additionally, we aim to identify the ethical considerations and safeguards that should be implemented when deploying ChatGPT in educational contexts. Furthermore, we will examine how the integration of ChatGPT affects the role of educators and the teaching-learning process. By addressing these research questions, we seek to understand the impact and implications of incorporating ChatGPT into educational environments.

1. What are the perceived benefits and challenges of using ChatGPT as a conversational AI tool in educational settings?

2. How does the use of ChatGPT in education influence student engagement and learning outcomes?

3. What ethical considerations and safeguards should be implemented when deploying ChatGPT in educational contexts?

4. How does the integration of ChatGPT affect the role of educators and the teaching-learning process?

The Populations, Interventions, Comparators, Outcomes, and Study Designs (PICOS) framework for our systematic review is outlined as follows:

• Population: ChatGPT users in educational settings, including teachers and students.

• Intervention: Using ChatGPT in the classroom as a conversational AI tool.

• Comparator: Inferred comparisons are made between educational environments with and without AI tools and between pre- and post-integration outcomes.

• Outcomes: educator adaptation, student engagement and learning outcomes, and ethical considerations.

• Study Designs: The review focuses on various study designs included in the selected papers, ranging from qualitative analyses to mixed-methods approaches

3.2 Search strategy

The search method utilized in this survey can be described in detail as follows:

3.2.1 Search terms

We used specific search terms related to our research questions for the survey. We also explored additional terms from specialized resources and used Boolean operators like “AND” and “OR” to refine the search results. This approach helped us find relevant articles and gather a comprehensive range of literature for our study

• “AI” OR “Artificial intelligence” AND “Chatgpt” OR “NLP”

• “Machine learning” AND “Chatgpt.”

• “Academia” AND “Chatgpt”

• “Education” AND “Chatgpt”

• “Large Language models “AND “Chatgpt” AND “artificial intelligence” OR “AI”

• “Open Ai” AND “Chatgpt”

• “GPT4” OR “Chatgpt” AND “education”

3.2.2 Survey resources

To locate the required research articles, we referred to the following digital libraries: IEEE Explorer, Springer, Elsevier Science Direct, ACM Digital Library, and SSRN.

3.2.3 Search phase

The research articles were found in the relevant digital libraries using the earlier search criteria. After applying inclusion and exclusion criteria, 70 sources were included in this study.

3.3 Study selection

After applying the search criteria, we obtained a list of approximately 729 publications. However, we conducted a rigorous screening process to retain only the relevant articles, resulting in a final selection of 70 papers published between 2022 and 2023. The following outlines the steps involved in the filtration and selection process:

• Elimination of duplicate articles obtained from different libraries and authors.

• Application of inclusion and exclusion criteria to remove irrelevant articles and retain those that meet the inclusion criteria.

• Inclusion of high-quality papers that adhere to quality evaluation guidelines.

• Continually search for comparable articles and repeat steps 3 and 4 on the newly identified articles.

Table 2 shows the criteria used during the inclusion and exclusion phases.

Table 2 . Exclusion and inclusion criteria.

3.4 Quality assessment rules

Quality Assessment Rules (QARs) were utilized to assess the obtained articles’ suitability in addressing the study questions. A set of 10 QARs was created, with each rule assigned a maximum score of 1 out of 10. The scoring was based on the following formula: “completely responded” = 1, “above average” = 0.75, “average” = 0.5, “below average” = 0.25, and “not answered” = 0. The article’s overall score was calculated by summing the points obtained from all 10 QARs. If the total score was five or above, the article was deemed acceptable; otherwise, it was excluded. The selected research articles and their respective QAR scores can be found in Table 9 in Appendix A .

QAR1: Are the research objectives related to ChatGPT clearly stated?

QAR2: Is the ChatGPT model version and architecture identified?

QAR3: Is the scope and application of ChatGPT in the study well-defined?

QAR4: Are the methodologies used to evaluate ChatGPT’s performance clearly described?

QAR5: Are the strengths of ChatGPT in the context of the study well explained?

QAR6: Are the limitations of ChatGPT in the context of the study well explained?

QAR7: Are the evaluation metrics and testing results for ChatGPT reported?

QAR8: Are the recommendations and future directions of ChatGPT in the context of the study well explained?

QAR9: Are the evaluation metrics for ChatGPT compared to other methods or models?

QAR10: Does the study contribute to understanding ChatGPT’s potential and limitations in the academic community or industry?

3.5 Data extraction strategy

The compiled list of articles was the basis for extracting the relevant information to address the research questions. Each article’s title, publication year, publication type, publisher source, description, keywords, paper theme related to RQ1, limitations associated with RQ2, advantages/opportunities associated with RQ3, and recommendations related to RQ4 were among the data retrieved from each paper. However, it is essential to note that not all articles addressed all the research questions.

3.6 Synthesis of extracted data

The extracted data for each research question were synthesized to analyze and summarize the findings related to paper themes, limitations, advantages, and recommendations. For RQ1, the paper themes were identified by categorizing the main topics explored in each publication. RQ2 involved examining the limitations mentioned in the articles to identify common challenges or shortcomings associated with using ChatGPT in education. In addressing RQ3, the advantages or opportunities of using ChatGPT in education were synthesized to understand the positive impacts and potential benefits. For RQ4, recommendations were gathered, combining qualitative insights and quantitative data, to provide practical suggestions for deploying and implementing ChatGPT in educational settings. Synthesis of this data gave a comprehensive understanding of the paper’s themes, limitations, advantages, and recommendations concerning ChatGPT’s use in education.

4 Results and discussion

The outcomes and findings of this survey will be discussed in the following subsection for each RQ.

4.1 Benefits and challenges of using ChatGPT in education

In this RQ, we aim to investigate the benefits and challenges of using ChatGPT, which researchers have widely studied. After reviewing each selected research article and analyzing it, we plotted a bar chart of the frequency of each benefit and challenge we found in each paper, represented in Figures 5 , 6 . According to Figure 5 , based on the analysis of the selected research articles, the most frequent benefit identified in the papers is that ChatGPT enhances learning. This indicates that researchers have found evidence suggesting that using ChatGPT in various applications positively impacts learning ( Kasneci et al., 2023 ). This benefit could refer to how ChatGPT can be used as a virtual tutor or assistant to provide users with personalized and interactive learning experiences ( Hopkins et al., 2023 ). Another benefit often associated with using ChatGPT, which could be included in the analysis, is improved access to information. ChatGPT can act as a conversational interface, allowing users to ask questions and receive relevant information quickly and conveniently.

Figure 5 . The benefits of ChatGPT.

Figure 6 . The challenges of ChatGPT.

With ChatGPT, users can access a wide range of information without the need to navigate through complex interfaces or conduct extensive searches ( O’Connor and ChatGPT, 2023 ). The conversational nature of ChatGPT allows for natural language queries, making it easier for users to express their information needs and obtain the desired information more conversationally and interactively. Additionally, ChatGPT can be integrated with various data sources and APIs, enabling it to retrieve real-time information or access specific databases. This can be particularly beneficial in domains where up-to-date information is crucial, such as news, weather updates, etc.

Overall, improved access to information is a significant advantage of ChatGPT, as it simplifies retrieving data and enables users to obtain relevant answers more efficiently.

According to Figure 6 , which represents the frequency of challenges associated with ChatGPT, it is observed that the most common challenges identified in the research articles are:

ChatGPT faces several challenges that must be addressed to improve its performance and ethical considerations. One such challenge is the presence of biases in AI models, including ChatGPT. Language models are trained on vast amounts of text data, which may inadvertently contain tendencies in the data sources. These biases can lead to unfair or discriminatory responses generated by ChatGPT. Addressing biases requires careful data curation, identification, and mitigation techniques to ensure fairness and inclusivity in the AI model’s responses.

Another significant challenge is the need for more accuracy in ChatGPT’s responses. While language models generate text based on patterns observed in their training data, they need proper understanding or knowledge. Consequently, they may need accurate or correct information in certain situations. Achieving higher accuracy involves advancing training methodologies, accessing reliable and diverse datasets, and developing mechanisms to verify and fact-check the data generated by ChatGPT ( Ahn, 2023 ).

The lack of emotional intelligence is another challenge for ChatGPT. It may need help understanding and appropriately responding to emotional cues expressed during conversations. Emotions play a vital role in human communication, and the absence of emotional intelligence in ChatGPT hinders its ability to provide sensitive responses. Enhancing emotional intelligence requires incorporating affective computing techniques, sentiment analysis, and the capability to recognize and respond to users’ emotional states.

Additionally, ChatGPT models often lack critical thinking abilities. While they can generate coherent responses, they may need help with complex queries requiring deeper analysis, reasoning, or inference. Advancing essential thinking capabilities involves exploring techniques such as knowledge incorporation, logical reasoning, and the ability to handle abstract or ambiguous queries ( Zielinski et al., 2023 ) effectively.

Ethical considerations are a multifaceted challenge when using ChatGPT. Transparency ensures users know they interact with an AI system and understand its limitations and capabilities. Accountability involves addressing responsible development, deployment, and use of AI models like ChatGPT. Safeguarding user privacy and data protection is essential for maintaining user trust. Additionally, measures must be in place to prevent the malicious use of biased applications of ChatGPT.

Addressing these challenges requires collaborative efforts from researchers across various disciplines, including AI, ethics, psychology, linguistics, and more. It involves refining model architectures, improving training methodologies, incorporating external knowledge sources, developing robust evaluation metrics, and implementing guidelines and regulations for responsible AI development and deployment.

By actively working on these challenges, researchers aim to enhance the benefits of ChatGPT while mitigating its limitations. This approach paves the way for more reliable, accurate, and ethically conscious conversational AI systems.

4.2 Student engagement and learning outcomes influence of ChatGPT in education

The use of ChatGPT in education has the potential to influence student engagement and learning outcomes greatly. By analyzing the provided paragraph and considering the available literature, it becomes evident that ChatGPT’s advanced capabilities contribute to enhanced educational experiences. One significant factor is the program’s ability to provide personalized student interaction. Through tailored responses and prompt feedback, ChatGPT creates an interactive learning environment that captures students’ attention and encourages active participation ( Looi, 2023 ).

Moreover, ChatGPT’s extensive knowledge base allows it to quickly generate accurate and relevant information. This accessibility to a wide range of knowledge empowers students to explore diverse perspectives and engage in critical thinking. ChatGPT supports students in understanding complex concepts by providing comprehensive and up-to-date information, thereby improving their learning outcomes.

Furthermore, ChatGPT’s availability and quick response time significantly impact student engagement ( Zielinski et al., 2023 ). Unlike traditional methods, where students may need to search for information through web browsing or rely on human assistance, ChatGPT provides immediate answers and guidance. This convenience saves time and keeps students actively engaged in learning, as they can access information whenever needed.

However, it is crucial to acknowledge the limitations and challenges associated with using ChatGPT in education. At the same time, the program’s impressive capabilities should be seen as a partial substitute for human educators. The importance of human interaction, guidance, and mentorship must be supported. Maintaining a balance between AI and human involvement is essential to ensure a holistic learning experience that addresses academic and socio-emotional needs.

Furthermore, the accuracy and reliability of the information generated by ChatGPT should be carefully considered. As with any AI system, “garbage in, garbage out” applies. If the program is trained on inaccurate or biased data, it may produce misleading or incorrect information ( Ahn, 2023 ). Therefore, it is crucial to validate and verify the information provided by ChatGPT through reputable sources and critical analysis.

In conclusion, the use of ChatGPT in education has the potential to influence student engagement and learning outcomes positively. Its personalized interaction, prompt responses, and access to a wide range of knowledge contribute to an enriched learning experience. However, it is essential to balance AI and human involvement and critically evaluate the information provided by ChatGPT. By harnessing AI’s power while embracing human educators’ invaluable role, we can create a learning environment that maximizes student engagement and fosters meaningful learning outcomes. Based on the selected articles, we categorized the factors previously discussed and presented them in Table 3 . Table 3 summarizes the main points discussed in the paragraph, highlighting the factors influencing student engagement and learning outcomes when using ChatGPT in education.

Table 3 . Influence of ChatGPT in education.

4.3 Ethical considerations and safeguards in deploying ChatGPT in education

When deploying ChatGPT or similar AI chatbots in educational contexts, it is crucial to establish a comprehensive framework of ethical considerations and safeguards to ensure responsible and beneficial use. Clear guidelines and policies should be developed to outline the appropriate use of AI-generated content, including any limitations or restrictions. This helps establish a standardized approach to the deployment of ChatGPT and ensures that its use aligns with ethical principles.

Human supervision plays a vital role in the responsible deployment of ChatGPT. Teachers or educators should be actively involved in the process ( Huang et al., 2023 ), providing guidance and oversight to ensure the accuracy and integrity of the content generated by the AI chatbot. Their involvement helps prevent the dissemination of misinformation or biased information, as they can intervene when necessary and provide additional context or clarification to the students.

Proper training and awareness programs should be provided to teachers and educators using ChatGPT. They should be familiarized with the capabilities and limitations of the AI chatbot and trained to understand the potential biases ( Khan et al., 2023 ) and errors that can arise from AI-generated content. By being well-informed, they can effectively utilize the tool and address ethical concerns.

Encouraging critical thinking and evaluation skills among students is crucial when utilizing ChatGPT in an educational context. Students should be taught to approach the information generated by the AI chatbot with a discerning mindset, questioning and verifying its accuracy through independent research and analysis. This empowers them to develop critical thinking skills and avoid mindlessly accepting information provided by AI systems.

Privacy and data protection should be paramount when deploying ChatGPT in an educational setting. Educational institutions must prioritize students’ privacy and ensure their personal information is securely stored and protected. Data encryption, access controls, and compliance with relevant data protection regulations should be in place to safeguard student data.

Regular monitoring and evaluation of the use of ChatGPT should be conducted to assess its effectiveness and address any ethical concerns that may arise. This monitoring can involve reviewing the interactions between students and the AI chatbot, analyzing the quality and accuracy of the generated content, and gathering feedback from both students and teachers. By actively monitoring its performance, institutions can identify and address issues, refine the system, and enhance the overall user experience.

Transparency, source attribution, user education, and regular review and auditing processes are additional components that contribute to the ethical deployment of ChatGPT ( Khan et al., 2023 ). Transparently informing users that they are interacting with an AI chatbot and establishing clear attribution guidelines for sources the system uses promote transparency and academic integrity. User education programs should be implemented to familiarize students with AI chatbots’ capabilities and limitations and encourage responsible use. Regular review and auditing processes help ensure ongoing adherence to ethical guidelines and provide opportunities for improvement and refinement.

By integrating these ethical considerations and safeguards, educational institutions can foster responsible use of AI chatbots, maintain ethical standards, and enhance the overall learning experience for students. By establishing clear guidelines, providing human supervision, promoting critical thinking skills, prioritizing privacy, conducting regular monitoring, and upholding transparency, institutions can harness the benefits of AI technology while mitigating potential risks and ethical concerns—also, a scientific paper talks about academic integrity consideration ( Helberger and Diakopoulos, 2023 ). After analyzing the ethical considerations discussed within the selected articles, the results are shown in the following tables. These tables provide an alternative representation of the ethical considerations and safeguards discussed in the paragraph. Table 4 focuses on ethical considerations, such as clear guidelines, human supervision, training, critical thinking, and privacy. Table 5 highlights the corresponding safeguards and actions, including monitoring, transparency, user education, and regular review and auditing processes.

Table 4 . Ethical Considerations in Deploying ChatGPT in Education.

Table 5 . Safeguards in deploying ChatGPT in education.

4.4 ChatGPT effects on educators and teachers

The integration of ChatGPT in teaching and learning can significantly impact educators’ roles and the entire teaching-learning process. ChatGPT can revolutionize traditional instructional practices with its interactive and conversational capabilities and open new possibilities for personalized and engaging learning experiences.

One of the critical ways ChatGPT affects educators’ roles is by shifting their focus from being the primary sources of information to becoming facilitators and guides ( DiGiorgio and Ehrenfeld, 2023 ). Instead of simply delivering content, educators can now assist students in navigating their interactions with ChatGPT. They can provide guidance on formulating practical questions, help students interpret and analyze the responses generated, and facilitate meaningful discussions based on the information provided. This transition empowers educators to take on a more active role in supporting and scaffolding student learning experiences.

Moreover, the integration of ChatGPT enables personalized and differentiated learning. Students can ask questions in their own words and receive tailored responses based on their specific formulations. This feature allows educators to address individual student needs and provide targeted support. By analyzing the responses generated by ChatGPT, educators can gain insights into students’ understanding and adapt their instructional strategies, fostering personalized learning experiences that cater to each student’s unique requirements.

In addition to personalized learning, ChatGPT promotes the development of inquiry and questioning skills among students. Educators can guide students in formulating practical questions and help them interpret and analyze the responses they receive. Conversations with ChatGPT encourage students to think critically, evaluate information, and refine their questioning techniques. This process enhances their ability to ask thoughtful and relevant questions and cultivates a deeper understanding of the subject matter.

Educators integrating ChatGPT into their teaching practices must monitor and assess how students use this technology as a learning tool. Educators can gain valuable insights into students’ learning processes by observing the types of questions asked, the quality of responses received, and the level of student engagement. This monitoring enables educators to provide timely feedback, address misconceptions, and ensure that students are effectively leveraging ChatGPT to enhance their learning outcomes.

It is important to note that the integration of ChatGPT also raises ethical considerations. Educators must guide students in using AI technologies like ChatGPT responsibly and ethically. This involves discussing privacy, data security, and potential biases in the training data that may impact the responses generated. By facilitating conversations around these ethical considerations, educators play a vital role in fostering digital literacy, responsible AI usage, and ethical decision-making.

In conclusion, the integration of ChatGPT in teaching and learning has transformative implications for the role of educators and the teaching-learning process. By shifting the focus from content delivery to facilitation and guidance, educators can empower students to participate in their learning actively. The personalized and differentiated nature of ChatGPT allows educators to address individual student needs, while its conversational capabilities promote inquiry and questioning skills. However, educators must also be mindful of the ethical considerations associated with using AI technologies and guide students in their responsible and ethical usage. With thoughtful integration and guidance, ChatGPT has the potential to revolutionize interactive learning environments and create engaging and personalized educational experiences. Also, this paper suggests what faculty should do to improve the educational role ( McGee, 2023a ). Based on the most frequent impact discussed in the selected articles, we categorize the aspects in Tables 6 , 7 . Table 6 represents the impact of ChatGPT on educators’ positions, and Table 7 represents ChatGPT integration’s benefits.

Table 6 . Impact of ChatGPT on teachers’ role.

Table 7 . Student-centric benefits of ChatGPT integration.

4.5 Findings

The first set of findings underscores the potential of integrating ChatGPT with other AI technologies to enhance human-computer interactions, enabling personalized responses and intuitive experiences ( Aljanabi and ChatGPT, 2023 ). This integration has transformative impacts across various domains ( Thorp, 2023 ). In education, ChatGPT fosters dynamic learning environments, promoting deep engagement and reflective thinking among students, thus creating opportunities for innovative teaching methods ( Ollivier et al., 2023 ).

ChatGPT’s adaptive capabilities enable personalized learning experiences tailored to individual student needs, fostering inclusive education, and enhancing motivation and academic performance ( Pericles ‘asher’ Rospigliosi, 2023 ). It also plays a significant role in academic writing processes, assisting researchers in drafting, summarizing, and conducting literature reviews ( Bin Arif et al., 2023 ). Concerns regarding the accuracy and integrity of AI-generated scientific writing are addressed, emphasizing the importance of robust fact-checking and verification processes ( Alkaissi and McFarlane, 2023 ).

Exploration of ChatGPT’s potential in detecting implicit hateful speech is noted, with caution urged in its utilization as a data annotation tool to prevent potential misinformation ( Fijačko et al., 2023 ). Ethical considerations loom large in the discussion surrounding ChatGPT’s deployment, with responsible usage and ethical implications emphasized ( DiGiorgio and Ehrenfeld, 2023 ).

Despite its benefits, challenges with ChatGPT include biases in AI models, the need for accuracy in responses, lack of emotional intelligence, and the absence of critical thinking abilities ( Ahn, 2023 ). In education, human supervision is deemed crucial to ensure the accuracy and integrity of generated content ( Huang et al., 2023 ). Training programs for educators are necessary to understand the capabilities and limitations of ChatGPT and address potential biases in AI-generated content ( Khan et al., 2023 ).

Ethical considerations extend to promoting critical thinking skills among students and safeguarding privacy and data protection ( Helberger and Diakopoulos, 2023 ). Integration of ChatGPT in teaching shifts educators’ roles from content delivery to facilitation and guidance, promoting personalized and differentiated learning experiences ( McGee, 2023a ). Overall, Table 8 presents a synthesis of findings from various research papers, each contributing to our understanding of the applications and implications of integrating ChatGPT in different contexts.

Table 8 . Summary of key findings.

5 Conclusion

This systematic literature review studied the impact of ChatGPT in education by reviewing 70 scientific research articles published between 2022 and 2023. The review focused on several perspectives, including the benefits and challenges of ChatGPT, student engagement, learning outcomes, ethical considerations, safeguards, and the effects of ChatGPT on educators and teachers. By synthesizing the findings and observations from these articles, valuable insights were gained regarding the efficient use of ChatGPT in educational settings.

In response to the first RQ, it aims to explore the positive impacts of ChatGPT in education, focusing on enhanced learning and improved information access. It also addresses challenges, including biases in AI models, accuracy issues, emotional intelligence, critical thinking limitations, and ethical concerns. The goal is to identify methods to enhance ChatGPT’s performance while promoting ethical and responsible use in educational settings.

This second RQ investigates ChatGPT’s impact on education. It examines personalized interaction, quick knowledge access, and immediate responses to student engagement and learning outcomes. While AI’s advantages are recognized, maintaining balance with human educators is essential. Ensuring information accuracy from ChatGPT is also emphasized. The goal is an enriched learning experience, maximizing student engagement and meaningful outcomes through effective AI-human collaboration.

Moving on to the third RQ, Deploying AI chatbots in education demands an ethical framework with content guidelines, preventing misinformation. Teacher supervision ensures accuracy, while training raises AI awareness and tackles biases. Empowering critical thinking enables students to verify information independently. Privacy and data protection are paramount, and regular monitoring addresses ethical concerns. Transparency, education, and reviews foster responsible AI use for a positive and secure learning experience.

Finally, the fourth RQ focused on the effects of ChatGPT on educators and teachers. They assist students in personalized learning with ChatGPT, fostering critical thinking and understanding. Educators monitor usage, offer feedback, and address ethical considerations, promoting digital literacy. Thoughtful integration creates engaging and personalized learning environments, empowering students and enhancing the overall educational experience.

In conclusion, this systematic literature review highlights the potential benefits, challenges, ethical considerations, and effects of integrating ChatGPT in education. It underscores the importance of addressing challenges, establishing ethical guidelines, and leveraging the strengths of ChatGPT while recognizing the vital role of human educators. By doing so, educational institutions can harness the advantages of ChatGPT to enhance student engagement, improve learning outcomes, and foster responsible and ethical use of AI technology in education.

Data availability statement

The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation.

Author contributions

AM: Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Project administration, Resources, Supervision, Validation, Writing – review & editing. MA: Conceptualization, Formal analysis, Funding acquisition, Investigation, Project administration, Software, Supervision, Validation, Writing – review & editing. AS: Data curation, Formal analysis, Methodology, Resources, Software, Visualization, Writing – original draft. FD: Conceptualization, Formal analysis, Methodology, Project administration, Supervision, Validation, Writing – original draft, Writing – review & editing.

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. This work was supported by University of Sharjah, OpenUAE Research and Development Group.

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher’s note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Supplementary material

The Supplementary material for this article can be found online at: https://www.frontiersin.org/articles/10.3389/feduc.2024.1379796/full#supplementary-material

Ahn, C. (2023). Exploring ChatGPT for information of cardiopulmonary resuscitation. Resuscitation 185:109729. doi: 10.1016/j.resuscitation.2023.109729

Crossref Full Text | Google Scholar

AlAfnan, M., Dishari, S., Jovic, M., and Lomidze, K. (2023). Chatgpt as an educational tool: opportunities, challenges, and recommendations for communication, business writing, and composition courses. J. Artif. Intellig. Technol. 3, 60–68. doi: 10.37965/jait.2023.0184

Aljanabi, M.ChatGPT (2023). ChatGPT: future directions and open possibilities. Mesopot. J. Cyber Secur. 2023, 16–17. doi: 10.58496/mjcs/2023/003

Alkaissi, H., and McFarlane, S. I. (2023). Artificial hallucinations in ChatGPT: implications in scientific writing. Cureus 15:2. doi: 10.7759/cureus.35179

Alshater, M. (2022). Exploring the role of artificial intelligence in enhancing academic performance: a case study of ChatGPT. SSRN Electron. J. doi: 10.2139/ssrn.4312358

Ante, L., and Demir, E. (2023). The ChatGPT effect on AI-themed cryptocurrencies. SSRN Electron. J. doi: 10.2139/ssrn.4350557

Aydın, Ö., and Karaarslan, E. (2022). OpenAI ChatGPT generated literature review: digital twin in healthcare. SSRN Electron. J. 2, 22–31. doi: 10.2139/ssrn.4308687

Aydın, Ö., and Karaarslan, E. (2023). Is beyond expectations, and undefined, “Is ChatGPT leading generative AI? What is beyond expectations?” Available at: https://papers.ssrn.com/

Google Scholar

Azari, A. (2022). ChatGPT usage and limitations. Hal Open Sci.

Badini, S., Regondi, S., Frontoni, E., and Pugliese, R. (2023). Assessing the capabilities of ChatGPT to improve additive manufacturing troubleshooting. Adv. Indus. Eng. Polymer Res. 6, 278–287. doi: 10.1016/j.aiepr.2023.03.003

Baidoo-Anu, D., and Owusu Ansah, L. (2023). Education in the era of generative artificial intelligence (AI): understanding the potential benefits of ChatGPT in promoting teaching and learning. SSRN Electron. J. 7, 52–62. doi: 10.2139/ssrn.4337484

Bin Arif, T., Munaf, U., and Ul-Haque, I. (2023). The future of medical education and research: is ChatGPT a blessing or blight in disguise? Med. Educ. 28:1. doi: 10.1080/10872981.2023.2181052

Bishop, L. (2023). A computer wrote this paper: what ChatGPT means for education, research, and writing. SSRN Electron. J. doi: 10.2139/ssrn.4338981

de Angelis, L., Baglivo, F., Arzilli, G., Privitera, G. P., Ferragina, P., Tozzi, A. E., et al. (2023). ChatGPT and the rise of large language models: the new AI-driven Infodemic threat in public health. SSRN Electron. J. 11:1166120. doi: 10.2139/ssrn.4352931

DiGiorgio, A. M., and Ehrenfeld, J. M. (2023). Artificial intelligence in medicine & ChatGPT: De-tether the physician. J. Med. Syst. 47, 1–2. doi: 10.1007/s10916-023-01926-3

Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., et al. (2023). ‘So what if ChatGPT wrote it?’ Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy. Int. J. Inf. Manag. 71:102642. doi: 10.1016/j.ijinfomgt.2023.102642

Fijačko, N., Gosak, L., Štiglic, G., Picard, C. T., and John Douma, M. (2023). Can ChatGPT pass the life support exams without entering the American heart association course? Resuscitation 185:109732. doi: 10.1016/j.resuscitation.2023.109732

Gozalo-Brizuela, R., and Garrido-Merchan, E. C. (2023). “ChatGPT is not all you need. A State of the Art Review of large Generative AI models.” arXiv [Preprint]. doi: 10.48550/arXiv.2301.04655

Haleem, A., Javaid, M., and Singh, R. P. (2022). An era of ChatGPT as a significant futuristic support tool: a study on features, abilities, and challenges. BenchCouncil Trans. Benchmarks, Stand. Eval. 2:100089. doi: 10.1016/j.tbench.2023.100089

Helberger, N., and Diakopoulos, N. (2023). ChatGPT and the AI act. Internet Policy Rev. 12:1. doi: 10.14763/2023.1.1682

Hopkins, A. M., Logan, J. M., Kichenadasse, G., and Sorich, M. J. (2023). Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectr. 7. doi: 10.1093/jncics/pkad010

Huang, F., Kwak, H., and An, J. (2023).“Is ChatGPT better than human annotators? Potential and limitations of ChatGPT in explaining implicit hate speech.” arXiv [Preprint]. doi: 10.1145/3543873.3587368

Huh, S. (2023). Issues in the 3rd year of the COVID-19 pandemic, including computer-based testing, study design, ChatGPT, journal metrics, and appreciation to reviewers. J. Educ. Eval. Health Profess. 20:5. doi: 10.3352/jeehp.2023.20.5

IEEE Spectrum (2023). “How ChatGPT could revolutionize academia.” Available at: https://spectrum.ieee.org/how-chatgpt-could-revolutionize-academia (Accessed: July 10, 2023).

Kasneci, E., Sessler, K., Küchemann, S., Bannert, M., Dementieva, D., Fischer, F., et al. (2023). ChatGPT for good? On opportunities and challenges of large language models for education. Learn. Individ. Differ. 103:102274. doi: 10.1016/j.lindif.2023.102274

Khan, R. A., Jawaid, M., Khan, A. R., and Sajjad, M. (2023). ChatGPT-reshaping medical education and clinical management. Pak. J. Med. Sci. 39, 605–607. doi: 10.12669/pjms.39.2.7653

Kitchenham, S., and Charters, B. (2007). “Guidelines for performing systematic literature reviews in software engineering.” Tech. report, Ver. 2.3 EBSE Tech. Report. EBSE.

Kohnke, L., Moorhouse, B. L., and Zou, D. (2023). ChatGPT for language teaching and learning. RELC J. 54, 537–550. doi: 10.1177/00336882231162868

Lecler, A., Duron, L., and Soyer, P. (2023). Revolutionizing radiology with GPT-based models: current applications, future possibilities and limitations of ChatGPT. Diagn. Interv. Imag. 104, 269–274. doi: 10.1016/j.diii.2023.02.003

Lee, H. (2023). The rise of ChatGPT: exploring its potential in medical education. Anat. Sci. Educ. doi: 10.1002/ase.2270

Lo, C. K. (2023). What is the impact of ChatGPT on education? A rapid review of the literature. Educ. Sci. 13:410. doi: 10.3390/educsci13040410

Looi, M. K. (2023). Sixty seconds on ChatGPT. BMJ 380:p205. doi: 10.1136/bmj.p205

Lubowitz, J. H. (2023). ChatGPT, An artificial intelligence Chatbot, is impacting medical literature. Arthrosc. J. Arthrosc. Relat. Surg. 39, 1121–1122. doi: 10.1016/j.arthro.2023.01.015

McGee, R. W. (2023a). Who were the 10 best and 10 worst U.S. presidents? The opinion of chat GPT (artificial intelligence). SSRN Electron. J. doi: 10.2139/ssrn.4367762

McGee, R. W. (2023b). Is chat Gpt biased against conservatives? An empirical study. SSRN Electron. J. doi: 10.2139/ssrn.4359405

Megahed, F. M., Chen, Y.-J., Ferris, J. A., Knoth, S., and Jones-Farmer, L. A. (2023). “How generative AI models such as ChatGPT can be (Mis)used in SPC practice, education, and research? An exploratory study.” arXiv [Preprint]. doi: 10.1080/08982112.2023.2206479

Mhlanga, D. (2023). Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning. SSRN Electron. J. 11, 324–339. doi: 10.2139/ssrn.4354422

O’Connor, S.ChatGPT (2023). Open artificial intelligence platforms in nursing education: tools for academic progress or abuse? Nurse Educ. Pract. 66:103537. doi: 10.1016/j.nepr.2022.103537

Ollivier, M., Pareek, A., Dahmen, J., Kayaalp, M. E., Winkler, P. W., Hirschmann, M. T., et al. (2023). A deeper dive into ChatGPT: history, use and future perspectives for orthopaedic research. Knee Surg. Sports Traumatol. Arthrosc. 31, 1190–1192. doi: 10.1007/s00167-023-07372-5

Pavlik, J. V. (2023). Collaborating with ChatGPT: considering the implications of generative artificial intelligence for journalism and media education. J. Mass Commun. Educ. 78, 84–93. doi: 10.1177/10776958221149577

Pericles ‘asher’ Rospigliosi (2023). Artificial intelligence in teaching and learning: what questions should we ask of ChatGPT? Interact. Learn. Environ. 31, 1–3. doi: 10.1080/10494820.2023.2180191

Ray, P. P. (2023). ChatGPT: a comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber Phys. Syst. 3, 121–154. doi: 10.1016/j.iotcps.2023.04.003

Sallam, M. (2023). ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare 11:887. doi: 10.3390/healthcare11060887

Salvagno, M., Taccone, F. S., and Gerli, A. G. (2023). Can artificial intelligence help for scientific writing? Crit. Care 27, 75. doi: 10.1186/s13054-023-04380-2

Shahriar, S., and Hayawi, K. (2023). “Let’s have a chat! A conversation with ChatGPT: technology, applications, and limitations.” arXiv [Preprint]. doi: 10.48550/arXiv.2302.13817

Sok, S., and Heng, K. (2023). ChatGPT for education and research: a review of benefits and risks. SSRN Electron. J. 3, 110–121. doi: 10.2139/ssrn.4378735

Sun, F. (2022). “ChatGPT, the start of a new era.” no. December, pp. 1–16.

Sun, G. H., and Hoelscher, S. H. (2023). The ChatGPT storm and what faculty can do. Nurse Educ. 48, 119–124. doi: 10.1097/nne.0000000000001390

Susnjak, T. (2022). “ChatGPT: the end of online exam integrity?” arXiv [Preprint]. doi: 10.48550/arXiv.2212.09292

Thorp, H. H. (2023). ChatGPT is fun, but not an author. Science 379:313. doi: 10.1126/science.adg7879

Yang, X., Li, Y., Zhang, X., Chen, H., and Cheng, W. (2023). “Exploring the limits of ChatGPT for query or aspect-based text summarization.” arXiv [Preprint]. doi: 10.48550/arXiv.2302.08081

Zhai, X. (2023). ChatGPT for next generation science learning. SSRN Electron. J. 29, 42–46. doi: 10.2139/ssrn.4331313

Zhu, D., Chen, J., Haydarov, K., Shen, X., Zhang, W., and Elhoseiny, M. (2023). “ChatGPT asks, BLIP-2 answers: automatic questioning towards enriched visual descriptions.” arxiv [Preprint]. doi: 10.48550/arXiv.2303.06594

Zielinski, C., Winker, M., Aggarwal, R., Ferris, L., Heinemann, M., Lapeña, Jr, J. F., et al. (2023). Chatbots, ChatGPT, and scholarly manuscripts: WAME recommendations on ChatGPT and Chatbots in relation to scholarly publications. Open Access Maced. J. Med. Sci. 11, 83–86. doi: 10.3889/oamjms.2023.11502

Keywords: conversational AI, ChatGPT, education, ethical considerations, human supervision

Citation: Bettayeb AM, Abu Talib M, Sobhe Altayasinah AZ and Dakalbab F (2024) Exploring the impact of ChatGPT: conversational AI in education. Front. Educ . 9:1379796. doi: 10.3389/feduc.2024.1379796

Received: 31 January 2024; Accepted: 17 June 2024; Published: 04 July 2024.

Reviewed by:

Copyright © 2024 Bettayeb, Abu Talib, Sobhe Altayasinah and Dakalbab. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Manar Abu Talib, [email protected]

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Genuine software, legally FREE - no cracking required!

Edit Word, Excel, and PPT effortlessly

Read, edit, and convert PDFs with the powerful PDF toolkit.

Microsoft-like interface, easy to use.

Windows • MacOS • Linux • iOS • Android

• Articles of Office solution

Step-by-step Guide to Using ChatGPT to Write a Report, Thesis and Dissertation

You must have heard or read about ChatGPT. What is it? A software or a magician? ChatGPT is an artificial intelligence chatbot developed and launched by OpenAI in November 2022. This chatbot can write answers, reports, codes, prompts, and more in seconds.

Moreover, it can write computer programs, compose music, teleplays, fairy tales, and write poetry and songs. It’s built with OpenAI’s GPT 3.5 and 4 families of large language models. The latest version of ChatGPT, released on 14th March 2023, is built on GPT 4 OpenAI model and can be purchased through a subscription for a specific time.

Benefits of using ChatGPT to write reports, theses, and dissertations

ChatGPT is a powerful artificial intelligence (AI) chatbot with many benefits. Today we shall be highlighting the benefits ChatGPT has on reports, theses, and dissertations.

Reports are professional documents submitted to an institute, department, company, and more. They are formal documents containing a written account of something observed or investigated. Below are some benefits of using ChatGPT to write reports.

Saves time:  ChatGPT saves your precious time; it writes your reports quickly and saves the time you would have spent researching and writing from the beginning.

Quality content:  The AI chatbot has been trained with massive data; hence it can write high-quality reports for you.

Variety of Styles:  Reports are usually long; thus, they can bore the reader if the content is not engaging. ChatGPT uses different styles, i.e., bullet points, lists, paragraphs, and more. This makes a report engaging.

Consistency and Productivity:  ChatGPT write the report in a consistent style and tone. This improves the readability of the report. Moreover, as ChatGPT saves your precious time, you can spend that time focusing on other tasks, improving your productivity.

Theses is a theory or personal research document. These are mainly written by university students proposing research papers on particular topics. Below are the benefits of using ChatGPT to write theses.

New idea:  ChatGPT helps you by providing a variety of ideas that can help you write your thesis. Moreover, the ideas can make your thesis stand out from others.

Guidance:  ChatGPT guides you throughout your thesis writing by providing references, and research material, summarising long research essays, and highlighting important points.

Writing Guidance:  The artificial intelligence model can advise and guide your style, tone, grammar, and more. ChatGPT guides you with this writing; further, it can proofread and rephrase your content.

3. Dissertation

Dissertation is a formal essay on a particular topic. It’s the same as the thesis and is mainly written and submitted by university students. Below are the advantages of using ChatGPT for writing a dissertation.

Knowledge:  ChatGPT is trained with vast knowledge and provides dissertation writers access to knowledge. The more diverse knowledge, the better dissertation.

Saves Time:  Dissertation writing is time-consuming; however, ChatGPT can generate texts for you instantly. You can ask ChatGPT to write sections, paragraphs, and particular dissertation headings. Moreover, it can proofread and check your dissertation's grammar, style, and errors.

Assistance with writing:  Dissertation requires a lot of time and effort. Moreover, quality is an essential factor you should keep in mind while writing a dissertation; chatGPT suggests ways to improve your dissertation writing. Moreover, ChatGPT can proofread, rephrase and highlight writing errors for you.

Step-by-Step Guide: Create a ChatGPT Account

Using ChatGPT might be complex; thus, we are here to help you. Below are steps to create an account and write reports and theses or dissertations.

1. Setting Up ChatGPT

Now that you know ChatGPT and its benefits associated with reports, theses, and dissertation writing, it’s time to set up a ChatGPT account.

The first thing to do is to visit the official website of OpenAI’s artificial intelligence chatbot ChatGPT.

After successfully landing on the official website of ChatGPT, you’ll see a login and sign-up option. You need to login in using your login credentials and progress further. However, if you do not have an account, click sign up, add an email, and create a password. Moreover, you’ll need to add your personal data, i.e., your date of birth, and verify your mobile number.

Afterward, you need to log in with the same email and password. OpenAI allows people to log in through Microsoft and Google accounts. If you have a valid Microsoft or Google account, simply click on login, click on Microsoft or Google, and log in to the selected account. Verify your phone number, and you’ll successfully log in to OpenAI to use ChatGPT.

After successfully logging in to OpenAI, you can start a new chat or use previous ones (if you logged in before and used chatbot). Click the new chat button on the left and start using the chatGPT. You can ask questions, gain knowledge, ask to proofread your work, suggest edits, and do more instantly.

If you are in a country where the use of ChatGPT is not allowed and you wish to register an account, you can refer to my other article " How to use Chatgpt ". It provides a detailed tutorial on how to register an account in such countries.

How to use ChatGPT to write a report

Setting up the ChatGPT account is easier than using it. Below we’ll guide you thoroughly on how to write a report using ChatGPT.

Setting up the Parameters

The first thing you must do is set parameters. What are the parameters? Parameters are framework or structure. You need to set up the report's parameters as they help control the report’s content and use other reports’ material in arguments. You need to tell ChatGPT where to start and let it know the limits of your report. In short, you need to provide ChatGPT with a structure under which it should generate your report.

Creating an Outline

Create an outline for your report. The outline may start with an introduction, having headings, bullet points, paragraphs, and more. You must provide an accurate outline to enable ChatGPT to write your report. This ensures that your report covers all the aspects in a good flow and all the required information. Without an outline, chatGPT may be unable to write it in a flow or may write something unnecessary for your report.

Writing the Report

The last thing is to ask ChatGPT to write the report for you. You need to set parameters, provide an outline, write a good prompt, and wait for ChatGPT to generate the report for you for a minute or two.

Topic: Impact of remote work on employee productivity

Purpose: To understand and examine the impact of remote work on the productivity of employees with findings and recommendations.

How to use ChatGPT to write a thesis or dissertation

As writing theses or dissertations is complex and requires time and energy, many people want to learn to use chatGPT to write them. Here’s how to write a thesis using Chatgpt.

Choosing a topic

After logging in to your OpenAI account, click on the new chat and choose a topic you want ChatGPT to write a thesis or dissertation on. This can be any topic that a normal human being can think of.

After deciding on a thesis or dissertation topic, you must create an outline. Creating an outline has its own benefits, as your theses will cover all aspects and topics in a flow, and the knowledge in the theses will be organized.

Writing the Thesis

Now that you have decided on a topic and created an outline, the next thing to do is write the thesis. Writing a good prompt will result in a good thesis. After writing a prompt for the thesis, click on the save and submit button, and wait a few minutes before ChatGPT can complete generating the thesis for you.

Topic: ChatGPT and its importance in conversational AI applications.

Purpose: To access and understand ChatGPT, its importance, benefits, and uses. Moreover, to examine its importance in conversational AI applications.

Now, you can use AI to assist you in generating a thesis, but it's important to note that you still need to carefully review the content generated by the AI to avoid any fabrication. Additionally, there are some universities that currently do not allow AI-generated theses. These universities may employ AI detection tools to check if a thesis was written by AI. In such cases, you can try using a paraphrasing tool to rewrite the AI-generated content until it passes the detection:

Recommended AI detection tools:  GPT-2 Output Detector

Recommended paraphrasing tools:  Quillbot

Perform another round of detection

Other AI or productivity tools recommended

There are various other AI or productivity tools that you can use instead of ChatGPT. Below are some.

1.  MidJourney

MidJourney is an artificial intelligence program that Mid Journey, Inc created and launched. The AI program can generate images and art using the prompts. You can use MidJourney for 20 free jobs to create or generate images for you on prompts. This software can help you create amazing images for your report and thesis. A thesis or report would look boring without images that engage the audience; hence you can use MidJourney AI to generate images for your thesis or report.

2.  WPS Office

WPS Office is a free office software that allows users to use Word, Excel, PPT, and PDF documents under a single roof. It’s free software that promotes creativity and boosts the productivity of users. The software has more than 500 million active users worldwide. The software lets users view, edit, translate, annotate, print, and do more. It’s compatible with Windows, MacOS, IOS, and Android.

Moreover, it’s free and has various advanced features and functions. The software enables users to write reports and a thesis using diverse tools. You can add bullet points, comments, and suggestions, highlight texts, and translate sentences and words. This is the best software for writing a report or dissertation, as it has templates for the report and thesis that can help you.

3. Chinchilla AI

Developed and launched by DeepMind in March 2022, this AI language model can better write your reports and thesis, requiring less computer power for interference and fine-tuning. The Chinchilla AI is said to outperform a number of traditional language models in terms of accuracy; hence, it can generate better and more accurate reports and a thesis for you. However, the software is currently in the testing phase and cannot be accessed by the general public.

A. Can I write a thesis with ChatGPT?

Yes. You can use ChatGPT to write a thesis. Start with choosing a topic, creating an outline, and writing a prompt to enable ChatGPT to generate a thesis on the topic for you.

B. Can I write a report with ChatGPT?

Yes. Writing a report using ChatGPT is possible and easy. All you need to do is set the report's parameters, create an outline, and submit a prompt to enable ChatGPT to generate the report.

C. How do you use ChatGPT to improve your writing?

ChatGPT can improve your writing by suggesting edits, proofreading, and suggesting new ideas. Moreover, ChatGPT can highlight errors too.

D. Can ChatGPT rewrite paragraphs?

Yes. ChatGPT is a powerful tool that can rewrite your texts better and make them more engaging and readable.

ChatGPT is a powerful artificial intelligence model that can help users with numerous tasks. So far, we have learned about ChatGPT and its benefits associated with report, thesis, or dissertation writing. Moreover, we learned how to write a thesis and report using ChatGPT. Setting up and using ChatGPT to write reports and thesis. The article also highlighted the best alternatives to ChatGPT for writing reports and thesis; one of them is  WPS Office .

• 1. How to Use WPS AI/Chatgpt to Write Research Papers: Guide for Beginners
• 2. How to Use WPS AI/Chatgpt to Write Essays: Guide for Beginners
• 3. How to Use Wps AI/Chatgpt to Write Technical Document: Guide for Beginners
• 4. Guide on How to Write or Create Annual Report in Word 2022
• 5. Ultimate Guide to Write A Seminar PDF Report
• 6. Guide on how to write or create weekly report in Excel 2022

15 years of office industry experience, tech lover and copywriter. Follow me for product reviews, comparisons, and recommendations for new apps and software.

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Clin Transl Med
• v.13(3); 2023 Mar
• PMC10028016

The future of ChatGPT in academic research and publishing: A commentary for clinical and translational medicine

1 School of Business and Law, Edith Cowan University, Perth Australia

2 Centre for Precision Health, Edith Cowan University, Perth Australia

ChatGPT, an artificial intelligence (AI)‐powered chatbot developed by OpenAI, is creating a buzz across all occupational sectors. Its name comes from its basis in the Generative Pretrained Transformer (GPT) language model. ChatGPT's most promising feature is its ability to offer human‐like responses to text input using deep learning techniques at a level far superior to any other AI model. Its rapid integration in various industries signals the public's burgeoning reliance on AI technology. Thus, it is essential to critically evaluate ChatGPT's potential impacts on academic clinical and translational medicine research.

1. ChatGPT'S INTRODUCTION TO MEDICAL RESEARCH

ChatGPT contains 175 billion parameters, making it one of the largest and most powerful models for AI processing available today—hence its growing use in different occupations. ChatGPT's responses are leaps and bounds above those from past AI programs, in no small part due to being more human‐like. ChatGPT has taken the business world by storm. It is easy to envision its expansion into clinical and translational medicine in the future. As such, experts must consider the potential effects of this technology in and beyond medical research.

ChatGPT has made its debut in the scientific literature through published papers and preprints. Although ChatGPT can undoubtedly benefit writers of all backgrounds, its limitations in medical research merit close attention. 1 The emerging use of ChatGPT has sparked an upheaval in the scientific community and ignited debates around the ethics of using AI to write scientific publications that can influence the decisions of physicians, researchers, and policymakers.

2. THE FACTUAL INACCURACIES OF ChatGPT

The most significant disadvantage of ChatGPT is that the information it compiles is not always accurate. This drawback is especially detrimental in academic publishing; after all, progress depends on sharing appropriate information. Presenting incorrect data in a scientific setting carries a great risk of harm. For example, research influences how personal and community health concerns are treated and managed.

The data which ChatGPT uses provide information from 2021 and earlier. The chatbot does not currently consider information reported in 2022 onward. 2 For a field that is driven by recent advances to boost knowledge, enhance interventions, and formulate evidence‐based policies, this year‐long (and growing) information gap is a stark hindrance. If scholars use ChatGPT to create content, attempting to publish papers that contain false or outdated information will tarnish authors’ credibility among colleagues and peers.

3. ChatGPT: NOT SO EASY TO DETECT

A double‐edged sword with ChatGPT is the ability—or more accurately, the inability—of scholars to detect when other professionals have used it. Researchers at Northwestern University asked ChatGPT to write 50 medical‐research abstracts based on a set of articles published in medical journals. The authors then asked a group of medical researchers to spot the fabricated abstracts. 3 Problematic results emerged, with human reviewers able to correctly identify only 68% of the ChatGPT‐produced abstracts and 86% of the genuine abstracts. These findings confirm ChatGPT writes believable (albeit potentially inaccurate) scientific abstracts.

The results of this study bode well for those interested in employing ChatGPT to facilitate the writing process, as people reading their work likely will not realize it was AI‐generated. However, this possibility raises several concerns. Being unable to identify valid information comes with consequences. Scientists may follow flawed investigation routes, which translate into wasted research dollars and misleading results. For policymakers, the inability to detect false research may ground policy decisions in incorrect information that could have monumental effects on society.

Due to these implications, the future of academic and scientific publishing may soon hold policies that forbid AI‐generated content. Those who use ChatGPT in any capacity will need to be aware of these mandates. The 40th International Conference on Machine Learning already banned papers written by AI tools, including ChatGPT. 4 The Science family of journals is also updating their license and Editorial Policies to specify that they will not allow ChatGPT‐produced text. They explained their stance in an editorial, stating that most cases of scientific misconduct arise from inadequate human attention, and permitting ChatGPT‐generated content significantly increases this risk. 5

4. AN AIDE FOR SCIENTIFIC INNOVATION

Not all ChatGPT‐related matters have elicited concern within the scientific research field. A February 2023 article in Nature described computational biologists’ use of ChatGPT to improve completed research papers. In just five minutes, the biologists received a review of their manuscript that increased readability and spotted equation‐based mistakes. During a trial with three manuscripts, the team's use of ChatGPT was not always smooth, but the final output returned better‐edited manuscripts. 6

Using ChatGPT for this purpose bypasses the scientific community's primary concerns surrounding AI and its use of inaccurate or outdated information. Because computational biologists initially wrote the manuscripts, the information was already accurate and up to date. ChatGPT can help increase researchers’ productivity and content quality. If scientists can spend less time editing their work, they can devote more time to advancing the field of medicine.

Considering these benefits, ChatGPT can prove invaluable for researchers looking to verify answers or identify problems in their work. It is important to remember that, as of now, ChatGPT is not sufficiently trained on specialized content to be able to fact‐check technical topics. 7

5. ChatGPT IN SCIENTIFIC RESEARCH AND PUBLISHING: THE PROS AND CONS

Experts anticipate that the technology and programs integrating ChatGPT will serve as precursors to more advanced AI systems. In the meantime, this chatbot can play a supportive role in academic and scientific publishing, primarily for editing. Even so, those who use ChatGPT must be aware of its limitations.

As it stands, ChatGPT cannot be relied upon to provide correct facts or produce reliable references, as stated by a January editorial in Nature Machine Intelligence . 8 Accepting the limitations of ChatGPT and using it only for certain tasks allows researchers to delegate tedious jobs, such as manuscript editing, to the AI model while avoiding catastrophes such as the publication of false information.

As ChatGPT becomes more commonplace, it will be crucial to calibrate expectations about its capabilities and acknowledge that it cannot take on every job. Especially in the academic research field, any tasks in need of specialized subject knowledge or innovative ideas and opinions still require a genuine human touch that cannot be replaced by AI.

6. ChatGPT AND CLINICAL AND TRANSLATIONAL MEDICINE

Our conclusions regarding ChatGPT and its applications in scientific research focus on a high‐impact journal– Clinical and Translational Medicine –that aims to promote, accelerate, and translate preclinical research for clinical applications. This journal highlights the importance of clinical and translational medicine research in the name of promoting the safety and efficacy of discoveries that proceed to human trials, reflecting the notion of ‘bench to bedside.’ 9 Implementing ChatGPT in its present iteration must be pursued with extreme caution given the tool's evolving limitations and capabilities when it comes to providing reliable information. Can AI replace human input? We concur with H. Holden Thorp's position 5 on ChatGPT in that “ChatGPT is fun, but not an author” (p. 313). Scientists might be able to use well‐developed AI tools to increase work efficiency for tasks such as proofreading and manuscript checks. In the future, AI‐based tools may become recognized for their contributions to broader areas of scientific research, depending on their abilities to support human input. The boundaries between research ethics and the moral use of AI in health research 10 need to be further explored to establish guidelines. All researchers and contributors must understand what AI can and cannot do. Therefore, editors and editorial board members should continue monitoring ChatGPT's applications in academic research to draft journal policies that inform contributors of best practices. Doing so will ensure that Clinical and Translational Medicine can maintain an image of integrity by publishing timely and accurate research that makes meaningful contributions. After all, research excellence is gauged by ethics and integrity.

CONFLICT OF INTEREST STATEMENT

The authors declare no conflict of interest.

Wen J, Wang W. The future of ChatGPT in academic research and publishing: A commentary for clinical and translational medicine . Clin Transl Med . 2023; 13 :e1207. 10.1002/ctm2.1207 [ PMC free article ] [ PubMed ] [ CrossRef ] [ Google Scholar ]

📚 Create A Research Project Report with ChatGPT [Prompt Included]

Here is the prompt you can use on GPT-4 to create the perfect Research Project Report

How to Create A Research Project Report with ChatGPT

👋 Welcome to the AI for Work's definitive guide on How to Create A Research Project Report with ChatGPT!

In this comprehensive walkthrough, we'll dive into the many facets of the Research Project Report :

• Using ChatGPT for: Research Project Report
• Understanding: What exactly is a Research Project Report ?
• Objective: The primary goal behind a Research Project Report
• Success Metrics: What defines a top-notch Research Project Report ?
• Structure: Crafting the perfect outline for your Research Project Report
• Reference Material: Essential reads to elevate your Research Project Report

Designed with a professional professor in the education department in mind, this prompt was written to harnesses the AI capabilities of GPT-4 to offer an expert level Research Project Report .

🔗 Go directly to the ChatGPT prompt: Research Project Report .

🎥 For a video tutorial on how the prompt works: https://www.youtube.com/watch?v=1O3iIdDLCaA&t=17s

How to Use the ChatGPT Prompt to Create a Research Project Report.

Step 1: Access the Prompt on AI for Work

Step 2: Once on the prompt page, click "copy prompt" and then paste it into the ChatGPT interface with the GPT-4 text model selected.

Step 3: ChatGPT will greet you with an initial message and present you with 5 questions. These questions are vital; they're designed to grasp a deep understanding of your specific needs. Ensure you answer with as much detail as possible.

Step 4: ChatGPT will use its knowledge base, your answers, and the key references to craft your Research Project Report.

Step 5: ChatGPT will then assess its own work against a stringent quality rubric to ensure it meets high standards. It will provide you with a table with its evaluation along with options to improve the Research Project Report.

These are the options and what each mean:

Option 1: Answer 3 More Questions to Personalize it More 🙋‍♂️:

• What You Get: An enhanced Research Project Report with additional layers of personalization.
• Why Use This: If you want more specificity or nuances addressed.
• Importance: Ensures your Research Project Report is uniquely tailored to your requirements.

Option 2: Evaluation from a Group of Experts 👑:

• What You Get: Feedback on the Research Project Report's quality from simulated industry experts.
• Why Use This: For alignment with industry standards and expert approval.
• Importance: Validates the quality and resonance of your Research Project Report with expert opinions.

Option 3: Simulate Feedback from a Focus Group 🧑‍🤝‍🧑:

• What You Get: Diverse feedback that mimics a broad audience's view.
• Why Use This: To gauge wider audience perception and improve accordingly.
• Importance: Provides diverse viewpoints, catering to a broader range of stakeholders.

Option 4: Let's Get Creative and Try Another Approach ✨:

• What You Get: A fresh perspective leading to a unique rendition of the Research Project Report.
• Why Use This: For a standout or unconventional version.
• Importance: Adds novelty, making your Research Project Report distinct and attention-grabbing.

Option 5: Make the Best Possible Research Project Report ⚡:

• What You Get: The pinnacle of quality, with ChatGPT delivering its best.
• Why Use This: For crucial presentations or pivotal projects.
• Importance: A flawless Research Project Report can significantly impact its reception.

Option 6: Request a Change in Format, Style, Length 💡:

• What You Get: A modified Research Project Report to your specifications.
• Why Use This: To match specific external requirements.
• Importance: Ensures your Research Project Report is versatile for various applications.

What is a {document} 📜?

A {document} refers to a written or printed piece of information that serves as a record or evidence of something. It can be in the form of a text file, a physical paper, or a digital document. The primary function of a {document} is to convey information, ideas, or instructions to its intended audience.

Why Do We Use a {document}? 🤔

There are several reasons why the use of a {document} is crucial in various scenarios, roles, departments, and industries. Some common situations where a {document} becomes essential include:

• Legal agreements and contracts: {Documents} play a vital role in formalizing agreements and contracts between individuals, organizations, or entities.
• Research and academic papers: {Documents} are used to present findings, theories, and scholarly work in a structured and organized manner.
• Business reports and proposals: {Documents} help in communicating business strategies, plans, financial information, and project proposals to stakeholders, clients, or investors.
• Official records and documentation: {Documents} are used to maintain records of important events, transactions, or processes in organizations, governments, or institutions.

Expert Advice on Crafting a {document} 🎓

Here are some tips and insights from experts on how to produce an effective {document}:

• Define your purpose: Clearly identify the purpose and objectives of your {document} before you start writing. This will help you maintain focus and ensure that your content aligns with your goals.
• Organize your content: Structure your {document} in a logical and coherent manner. Use headings, subheadings, and bullet points to make it easy for readers to navigate and understand the information.
• Use clear and concise language: Avoid jargon and technical terms unless necessary. Use simple and straightforward language to ensure that your {document} is accessible to a wide range of readers.

What are the Success Factors of an Excellent Research Project Report?

• Clear and well-defined research question or objective
• Thorough and comprehensive literature review
• Well-designed and appropriate research methodology
• Accurate and reliable data collection and analysis
• Logical and coherent presentation of findings and conclusions

What are the Must-Have Requirements When Creating a Research Project Report?

• Clearly state the research question or objective
• Conduct a thorough literature review to establish the context and relevance of the research
• Select and apply appropriate research methods and data collection techniques
• Analyze and interpret the collected data using appropriate statistical or qualitative analysis methods
• Present the findings, conclusions, and recommendations in a logical and organized manner

Detailed Outline for a Research Project Report

I. introduction.

A. Background information on the topic

B. Statement of the problem

C. Research objectives and questions

D. Significance and relevance of the study

II. Literature Review

A. Review of relevant theories and concepts

B. Summary of previous research studies

C. Identification of gaps in existing literature

D. Theoretical framework for the current study

III. Methodology

A. Research design (e.g., experimental, correlational, qualitative, etc.)

B. Sampling technique and sample size

C. Data collection methods (e.g., surveys, interviews, observations, etc.)

D. Data analysis techniques (e.g., statistical analysis, thematic analysis, etc.)

E. Ethical considerations and measures taken

IV. Results

A. Presentation of the collected data

B. Data analysis and interpretation

C. Findings related to the research objectives and questions

D. Use of visuals (tables, graphs, charts) to enhance understanding

V. Discussion

A. Comparison of findings with previous research

B. Explanation of results and their implications

C. Limitations of the study

D. Suggestions for future research

VI. Conclusion

A. Summary of the key findings

B. Reiteration of the research objectives and questions

C. Contribution to the field of study

D. Practical implications and recommendations

VII. References

A. List of all sources cited in the report

B. Proper formatting according to the chosen citation style (APA, MLA, etc.)

VIII. Appendices (if applicable)

A. Supporting materials such as survey questionnaires, interview transcripts, etc.

B. Additional data or information that supplements the main report

Note: The outline provided above is a general structure that can be adapted and modified based on the specific requirements of your research project. It is essential to consult your instructor or research supervisor for any specific guidelines or sections they may want you to include.

Recommended Resources for Creating a Research Project Report

If you are looking to create a Research Project Report, I would recommend these three books and here is exactly why:

• "How to Research" by Loraine Blaxter, Christina Hughes, and Malcolm Tight: This book provides a step-by-step guide on conducting research. It covers essential aspects such as formulating research questions, designing research methods, and analyzing data. One key emphasis of this book is the importance of thoroughness in research, ensuring that all relevant literature is reviewed and all necessary data is collected. Additionally, it offers practical advice on organizing and presenting research findings, including writing a clear and concise report. Ethical considerations in research are also highlighted, ensuring that the study is conducted ethically and with integrity.
• "Educational Research: Planning, Conducting, and Evaluating Quantitative and Qualitative Research" by John W. Creswell and J. David Creswell: This comprehensive book provides an overview of both quantitative and qualitative research methods commonly used in educational research. It emphasizes the importance of selecting appropriate research designs and methods based on the research questions and objectives. The book also offers guidance on data collection and analysis techniques, including surveys, interviews, observations, and statistical analysis. Validity and reliability in research are highlighted, ensuring that the findings are accurate and trustworthy. Furthermore, the book discusses the importance of reporting research findings in a clear and accessible manner, making them useful for policymakers and educators.
• "Improving Schools Through Action Research: A Reflective Practice Approach" by Cher C. Hendricks: This book focuses on action research as a powerful tool for improving educational practices and addressing real-world challenges in schools. It provides a framework for conducting action research, including identifying a problem, developing a research plan, implementing interventions, and reflecting on the outcomes. Collaboration and involving stakeholders in the research process are emphasized, ensuring that the findings are relevant and actionable. The book offers practical examples and case studies of successful action research projects in various educational settings. Furthermore, it highlights the significance of continuous improvement and reflective practice in educational research, promoting ongoing learning and growth.

These three books provide a comprehensive and practical guide to conducting research in the field of education. They cover various aspects of the research process, from formulating research questions to reporting findings. Whether you are a professor or a student working on a Research Project Report, these references will undoubtedly enhance your understanding and skills in educational research.

Key Terms for Research Project Report

Keyword 1: Research

Research refers to the systematic investigation and study of a particular subject or problem to establish facts, reach new conclusions, or contribute to existing knowledge. It involves the collection, analysis, and interpretation of data or information to answer research questions or test hypotheses.

Keyword 2: Project

A project is a planned and organized effort to achieve a specific objective or goal within a defined timeframe. In the context of a research project report, it refers to the overall study or investigation undertaken by a researcher or a group of researchers to address a research problem or question.

Keyword 3: Report

A report is a formal document that presents detailed information, findings, and analysis of a particular subject or research study. In the context of a research project report, it serves as a comprehensive account of the research process, methodology, results, and conclusions, providing a clear and structured overview of the study.

Keyword 4: Methodology

Methodology refers to the systematic and theoretical analysis of the methods, techniques, and procedures used in a research study. It outlines the overall approach and design employed to collect and analyze data, including the selection of research participants, data collection instruments, data analysis techniques, and ethical considerations.

Keyword 5: Findings

Findings are the results or outcomes obtained from the analysis and interpretation of data collected during a research study. They represent the empirical evidence or information that addresses the research questions or objectives. Findings are typically presented in a research project report using tables, graphs, or descriptive narratives to provide a clear understanding of the research outcomes.

Frequently Asked Questions about Creating a Research Project Report

Question 1 about Research Project Report:

What is a Research Project Report?

A Research Project Report is a document that presents the findings and analysis of a research project. It includes a detailed description of the research question, methodology, data collection and analysis methods, results, and conclusions.

Question 2 about Research Project Report:

What should be included in a Research Project Report?

A Research Project Report should include an introduction, literature review, research methodology, data analysis, results, discussion, and conclusion. Additionally, it should have a title page, abstract, table of contents, and references.

Question 3 about Research Project Report:

How should I structure my Research Project Report?

Your Research Project Report should have a clear and logical structure. Start with an introduction that provides background information and states the research question. Then, include a literature review to discuss previous research on the topic. Next, describe your research methodology, including the participants, data collection methods, and analysis techniques. Present your findings and analyze the results in the following sections. Finally, conclude the report by summarizing the key findings and their implications.

Question 4 about Research Project Report:

How should I format my Research Project Report?

Your Research Project Report should follow a specific formatting style, such as APA or MLA. Use 12-point font, double spacing, and include page numbers. Use headings and subheadings to organize the content, and include a title page with the project title, your name, and the date. Additionally, include a table of contents and a list of references at the end of the report.

Question 5 about Research Project Report:

How can I ensure the quality of my Research Project Report?

To ensure the quality of your Research Project Report, consider the following tips:

• Conduct thorough research and use reliable sources for your literature review.
• Clearly define your research question and objectives.
• Use appropriate research methodology and data collection methods.
• Analyze your data carefully and accurately.
• Interpret your findings objectively and provide evidence-based conclusions.
• Edit and proofread your report for grammar, spelling, and formatting errors.
• Seek feedback from your advisor or peers to improve the report's quality.

About the Author

Ali Abassi is a Prompt Engineer and Growth Marketer focused on the AI space. As the founder of AI for Work , Ali's vision is to empower employees to leverage the power of AI in their daily tasks and enhance the dynamics of workplace productivity using AI. For collaboration opportunities, reach out to Ali through the Contact Us page.

Additional Resources to Explore 🔍

• Prompts for the education department
• Prompts for a professional professor
• AI for Work Resource Page
• AI Automation Agency
• Learn How to Use AI at Work
• AI Agents Database
• Subscribe to the AI for Work Newsletter

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form .

How to make ChatGPT provide sources and citations

One of the biggest complaints about ChatGPT is that it provides information that is difficult to check for accuracy. Those complaints exist because ChatGPT doesn't provide the sources, footnotes, or links from which it derived the information in its answers.

While that is true for the GPT-3.5 model, GPT-4 and GPT-4o  provide more citation resources. While GPT-4 is only for paid subscribers, GPT-4o is available to both free and paid subscribers, although free users get fewer citations and less detail than users with a ChatGPT Plus subscription .

Also:  4 things Claude AI can do that ChatGPT can't  

Here's how ChatGPT describes the approach: "GPT-4o in free mode provides basic and essential citations, focusing on quick and concise references to ensure information is traceable. In contrast, GPT-4o in paid mode offers enhanced, detailed, and frequent citations, including multiple sources and contextual annotations to provide comprehensive verification and understanding of the information. This ensures a robust and reliable experience, especially beneficial for users requiring in-depth information and thorough source verification."

Even with the provided citations in GPT-4o, there are ways to improve your results.

1. Write a query and ask ChatGPT

To start, you need to ask ChatGPT something that needs sources or citations. I've found it's better to ask a question with a longer answer, so there's more "meat" for ChatGPT to chew on. 

Also: The best AI chatbots: ChatGPT and other interesting alternatives to try

Keep in mind that ChatGPT can't provide any information after January 2022 for GPT-3.5, April 2023 for GPT-4, and October 2023 for GPT-4o, and requests for information pre-internet (say, for a paper on Ronald Reagan's presidency) will have far fewer available sources.

Here's an example of a prompt I wrote on a topic that I worked on a lot when I was in grad school:

Describe the learning theories of cognitivism, behaviorism, and constructivism

2. Ask ChatGPT to provide sources

This is where a bit of prompt engineering comes in. A good starting point is with this query:

Please provide sources for the previous answer

I've found that this prompt often provides offline sources, books, papers, etc. The problem with offline sources is you can't check their veracity. Still, it's a starting point. A better query is this:

Please provide URL sources

This prompt specifically tells ChatGPT that you want clickable links to sources. You can also tweak this prompt by asking for a specific quantity of sources, although your mileage might vary in terms of how many you get back:

Please provide 10 URL sources

3. Push ChatGPT to give you higher-quality sources

Most large language models  respond well to detail and specificity . So if you're asking for sources, you can push for higher-quality sources. You'll need to specify that you need reliable and accurate sources. While this approach won't necessarily work, it may remind the AI chatbot to give you more useful responses. For example:

Please provide me with reputable sources to support my argument on... (whatever the topic is you're looking at)

You can also tell ChatGPT the kinds of sources you want. If you're looking for scholarly articles, peer-reviewed journals, books, or authoritative websites, mention these preferences explicitly. For example:

Please recommend peer-reviewed journals that discuss... (and here, repeat what you discussed earlier in your conversation)

When dealing with abstract concepts or theories, request that ChatGPT provide a conceptual framework and real-world examples. Here's an example:

Can you describe the principles of Vygotsky's Social Development Theory and provide real-world examples where these principles were applied, including sources for these examples?

This approach gives you a theoretical explanation and practical instances to trace the original sources or case studies.

Also: Two ways you can build custom AI assistants with GPT-4o

Another idea is to use sources that don't have link rot (that is, they're no longer online at the URL that ChatGPT might know). Be careful with this idea, though, because ChatGPT doesn't know about things after January 2022 for GPT-3.5, April 2023 for GPT-4, and October 2023 for GPT-4o. So, while you might be tempted to use a prompt like this:

Please provide me with sources published within the past five years.

Instead, consider using a prompt like this:

Please provide sources published from 2019 through April 2023.

And, as always, don't assume that whatever output ChatGPT gives you is accurate. It's still quite possible the AI will completely fabricate answers, even to the point of making up the names of what seem like academic journals. It's a sometimes helpful tool, but it's also  a fibber .

4. Attempt to verify/validate the provided sources

Keep this golden rule in mind about ChatGPT-provided sources: ChatGPT is more often wrong than right .

Across the many times I've asked ChatGPT for URL sources, roughly half were just plain bad links. Another 25% or more of the links went to topics completely or somewhat unrelated to the one I was trying to source. GPT-4 and GPT-4o are slightly more reliable, but not by much.

Also: How to use ChatGPT: Everything you need to know

For example, I asked for sources on a backgrounder for the phrase "trust but verify,"  generally popularized by US President Ronald Reagan. I got a lot of sources back, but most didn't exist. I got some back that correctly took me to active pages on the Reagan Presidential Library site, but the page topic had nothing to do with the phrase.

I had better luck with my learning theory question from step 1. There, I got back offline texts from people I knew from my studies who had worked on those theories. I also got back URLs. Once again, only about two in 10 worked or were accurate.

Also:  What does GPT stand for? Understanding GPT-3.5, GPT-4, GPT-4o, and more

Don't despair. The idea isn't to expect ChatGPT to provide sources that you can immediately use. If you instead think of ChatGPT as a research assistant, it will give you some great starting places. Use the names of the articles (which may be completely fake or just not accessible) and drop them into Google. That process will give you some interesting search queries that probably lead to interesting material that can legitimately go into your research.

Also, keep in mind that you're not limited to using ChatGPT. Don't forget all the tools available to researchers and students. Do your own web searches. Check with primary sources and subject-matter experts if they're available. If you're in school, you can even ask your friendly neighborhood librarian for help.

Also:  How to use ChatGPT to create an app

Don't forget that there are many excellent traditional sources. For example, Google Scholar and JSTOR  provide access to a wide range of academically acceptable resources you can cite with reasonable confidence.

One final point: if you merely cut and paste ChatGPT sources into your research, you're likely to get stung. Use the AI for clues, not as a way to avoid the real work of research.

How do you put sources in APA format? 

APA style is a citation style that's often required in academic programs. APA stands for American Psychological Association. I've often thought they invented these style rules to get more customers. The definitive starting point for APA style is the Purdue OWL , which provides a wide range of style guidelines.

Also:   GPT-3.5 vs GPT-4: Is ChatGPT Plus worth its subscription fee?

Be careful: online style formatters might not do a complete job, and you may get your work returned by your professor. It pays to do the work yourself -- and be careful doing it.

How can I make ChatGPT provide more reliable sources for its responses?

This is a good question. I have found that sometimes -- sometimes -- if you ask ChatGPT to give you more sources or re-ask for sources, it will give you new listings. If you tell ChatGPT the sources it provided were erroneous, it will sometimes give you better ones. The bot may also apologize and give excuses. Another approach is to re-ask your original question with a different focus or direction, and then ask for sources for the new answer.

Also: How to access, install, and use AI ChatGPT-4 plugins

Once again, my best advice is to avoid treating ChatGPT as a tool that writes for you and more as a writing assistant. Asking for sources to cut and paste a ChatGPT response is pretty much plagiarism. That said, using ChatGPT's responses, and any sources you can tease out, as clues for further research and writing is a legitimate way to use this tool.

Why are ChatGPT sources often so wrong? 

For some links, it's just link rot. Some links may have changed, since many sources are more than three years old. Other sources are of indeterminate age. Since we don't have a full listing of ChatGPT's sources, it's impossible to tell how valid they are or were. 

Also:   How does ChatGPT actually work?  

Since ChatGPT was trained mostly without human supervision , we know that most of its sources weren't vetted and could be wrong, made up, or completely non-existent.

Trust, but verify.

You can follow my day-to-day project updates on social media. Be sure to subscribe to my weekly update newsletter , and follow me on Twitter/X at @DavidGewirtz , on Facebook at Facebook.com/DavidGewirtz , on Instagram at Instagram.com/DavidGewirtz , and on YouTube at YouTube.com/DavidGewirtzTV .

More on AI tools

If you want a career in ai, start with these 5 steps, 5 ways amazon can make an ai-powered alexa subscription worth the cost, how to watch the 2024 summer olympics: all your streaming options.

• The University Of Chicago

• Visitors & Fellows
• BFI Employment Opportunities
• Big Data Initiative
• Chicago Experiments Initiative
• Health Economics Initiative
• Industrial Organization Initiative
• International Economics and Economic Geography Initiative
• Macroeconomic Research Initiative
• Political Economics Initiative
• Price Theory Initiative
• Ronzetti Initiative for the Study of Labor Markets
• Becker Friedman Institute China
• Becker Friedman Institute Latin America
• Macro Finance Research Program
• Development Innovation Lab
• Energy Policy Institute at the University of Chicago
• TMW Center for Early Learning + Public Health
• UChicago Scholars
• Visiting Scholars
• Saieh Family Fellows

Using data representing one-third of the world’s population, we find that extreme hot and cold days cause substantial labor supply declines for weather-exposed workers, but not for weather-protected workers. With these results and a simple theoretical framework, we calculate that...

Uncertainty, as it pertains to climate change and other policy challenges, oper-ates through multiple channels. Such challenges are commonly framed using social valuations such as the social cost of climate change and the social value of research and development. These...

Formal theory and empirical research are complementary in building and advancing the body of knowledge in accounting in order to understand real-world phenomena. We offer thoughts on opportunities for empiricists and theorists to collaborate, build on each other’s work, and...

• View All caret-right

Upcoming Events

2024 mfr program summer session for young scholars, ai in social science conference 2024, conference to honor the contributions of philip j. reny, past events, bfi student lunch series – the impact of incarceration on employment, earnings, and tax filing, macro financial modeling meeting spring 2012, modeling financial sector linkages to the macroeconomy, research briefs.

Interactive Research Briefs

• Media Mentions
• Press Releases
• Search Search

The Adoption of ChatGPT

Recent research from UChicago economists has revealed that the AI chatbot ChatGPT can excel at investing tasks including predicting corporate investment policies , processing dense corporate disclosures , and detecting corporate risk . Beyond investing, experts predict that ChatGPT will disrupt many high-skilled occupations, including journalism, IT support, human resources, and marketing. In this paper, the authors study the adoption of ChatGPT, providing descriptive and experimental evidence on who has already adopted ChatGPT, how workers anticipate it will affect their jobs, and why some workers use ChatGPT and others do not.

In collaboration with Statistics Denmark, the authors survey 100,000 workers from 11 occupations that are exposed to ChatGPT between November 2023 and January 2024. Their survey includes an experiment component in which they test whether informing workers about expert assessments of ChatGPT in their job tasks impacts their adoption of the tool. The authors link their survey responses to administrative data on participants’ labor market histories, earnings, wealth, education, and demographics.

Continue scrolling to explore their results:

ChatGPT: Everything you need to know about the AI-powered chatbot

ChatGPT, OpenAI’s text-generating AI chatbot, has taken the world by storm since its launch in November 2022. What started as a tool to hyper-charge productivity through writing essays and code with short text prompts has evolved into a behemoth used by more than 92% of Fortune 500 companies .

That growth has propelled OpenAI itself into becoming one of the most-hyped companies in recent memory. And its latest partnership with Apple for its upcoming generative AI offering, Apple Intelligence, has given the company another significant bump in the AI race.

2024 also saw the release of GPT-4o, OpenAI’s new flagship omni model for ChatGPT. GPT-4o is now the default free model, complete with voice and vision capabilities. But after demoing GPT-4o, OpenAI paused one of its voices , Sky, after allegations that it was mimicking Scarlett Johansson’s voice in “Her.”

OpenAI is facing internal drama, including the sizable exit of co-founder and longtime chief scientist Ilya Sutskever as the company dissolved its Superalignment team. OpenAI is also facing a lawsuit from Alden Global Capital-owned newspapers , including the New York Daily News and the Chicago Tribune, for alleged copyright infringement, following a similar suit filed by The New York Times last year.

Here’s a timeline of ChatGPT product updates and releases, starting with the latest, which we’ve been updating throughout the year. And if you have any other questions, check out our ChatGPT FAQ here.

Timeline of the most recent ChatGPT updates

February 2024, january 2024.

• ChatGPT FAQs

OpenAI delays ChatGPT’s new Voice Mode

OpenAI planned to start rolling out its advanced Voice Mode feature to a small group of ChatGPT Plus users in late June, but it says lingering issues forced it to postpone the launch to July. OpenAI says Advanced Voice Mode might not launch for all ChatGPT Plus customers until the fall, depending on whether it meets certain internal safety and reliability checks.

ChatGPT releases app for Mac

ChatGPT for macOS is now available for all users . With the app, users can quickly call up ChatGPT by using the keyboard combination of Option + Space. The app allows users to upload files and other photos, as well as speak to ChatGPT from their desktop and search through their past conversations.

The ChatGPT desktop app for macOS is now available for all users. Get faster access to ChatGPT to chat about email, screenshots, and anything on your screen with the Option + Space shortcut: https://t.co/2rEx3PmMqg pic.twitter.com/x9sT8AnjDm — OpenAI (@OpenAI) June 25, 2024

Apple brings ChatGPT to its apps, including Siri

Apple announced at WWDC 2024 that it is bringing ChatGPT to Siri and other first-party apps and capabilities across its operating systems. The ChatGPT integrations, powered by GPT-4o, will arrive on iOS 18, iPadOS 18 and macOS Sequoia later this year, and will be free without the need to create a ChatGPT or OpenAI account. Features exclusive to paying ChatGPT users will also be available through Apple devices .

Apple is bringing ChatGPT to Siri and other first-party apps and capabilities across its operating systems #WWDC24 Read more: https://t.co/0NJipSNJoS pic.twitter.com/EjQdPBuyy4 — TechCrunch (@TechCrunch) June 10, 2024

House Oversight subcommittee invites Scarlett Johansson to testify about ‘Sky’ controversy

Scarlett Johansson has been invited to testify about the controversy surrounding OpenAI’s Sky voice at a hearing for the House Oversight Subcommittee on Cybersecurity, Information Technology, and Government Innovation. In a letter, Rep. Nancy Mace said Johansson’s testimony could “provide a platform” for concerns around deepfakes.

ChatGPT experiences two outages in a single day

ChatGPT was down twice in one day: one multi-hour outage in the early hours of the morning Tuesday and another outage later in the day that is still ongoing. Anthropic’s Claude and Perplexity also experienced some issues.

You're not alone, ChatGPT is down once again. pic.twitter.com/Ydk2vNOOK6 — TechCrunch (@TechCrunch) June 4, 2024

The Atlantic and Vox Media ink content deals with OpenAI

The Atlantic and Vox Media have announced licensing and product partnerships with OpenAI . Both agreements allow OpenAI to use the publishers’ current content to generate responses in ChatGPT, which will feature citations to relevant articles. Vox Media says it will use OpenAI’s technology to build “audience-facing and internal applications,” while The Atlantic will build a new experimental product called Atlantic Labs .

I am delighted that @theatlantic now has a strategic content & product partnership with @openai . Our stories will be discoverable in their new products and we'll be working with them to figure out new ways that AI can help serious, independent media : https://t.co/nfSVXW9KpB — nxthompson (@nxthompson) May 29, 2024

OpenAI signs 100K PwC workers to ChatGPT’s enterprise tier

OpenAI announced a new deal with management consulting giant PwC . The company will become OpenAI’s biggest customer to date, covering 100,000 users, and will become OpenAI’s first partner for selling its enterprise offerings to other businesses.

OpenAI says it is training its GPT-4 successor

OpenAI announced in a blog post that it has recently begun training its next flagship model to succeed GPT-4. The news came in an announcement of its new safety and security committee, which is responsible for informing safety and security decisions across OpenAI’s products.

Former OpenAI director claims the board found out about ChatGPT on Twitter

On the The TED AI Show podcast, former OpenAI board member Helen Toner revealed that the board did not know about ChatGPT until its launch in November 2022. Toner also said that Sam Altman gave the board inaccurate information about the safety processes the company had in place and that he didn’t disclose his involvement in the OpenAI Startup Fund.

Sharing this, recorded a few weeks ago. Most of the episode is about AI policy more broadly, but this was my first longform interview since the OpenAI investigation closed, so we also talked a bit about November. Thanks to @bilawalsidhu for a fun conversation! https://t.co/h0PtK06T0K — Helen Toner (@hlntnr) May 28, 2024

ChatGPT’s mobile app revenue saw biggest spike yet following GPT-4o launch

The launch of GPT-4o has driven the company’s biggest-ever spike in revenue on mobile , despite the model being freely available on the web. Mobile users are being pushed to upgrade to its $19.99 monthly subscription, ChatGPT Plus, if they want to experiment with OpenAI’s most recent launch.

OpenAI to remove ChatGPT’s Scarlett Johansson-like voice

After demoing its new GPT-4o model last week, OpenAI announced it is pausing one of its voices , Sky, after users found that it sounded similar to Scarlett Johansson in “Her.”

OpenAI explained in a blog post that Sky’s voice is “not an imitation” of the actress and that AI voices should not intentionally mimic the voice of a celebrity. The blog post went on to explain how the company chose its voices: Breeze, Cove, Ember, Juniper and Sky.

We’ve heard questions about how we chose the voices in ChatGPT, especially Sky. We are working to pause the use of Sky while we address them. Read more about how we chose these voices: https://t.co/R8wwZjU36L — OpenAI (@OpenAI) May 20, 2024

ChatGPT lets you add files from Google Drive and Microsoft OneDrive

OpenAI announced new updates for easier data analysis within ChatGPT . Users can now upload files directly from Google Drive and Microsoft OneDrive, interact with tables and charts, and export customized charts for presentations. The company says these improvements will be added to GPT-4o in the coming weeks.

We're rolling out interactive tables and charts along with the ability to add files directly from Google Drive and Microsoft OneDrive into ChatGPT. Available to ChatGPT Plus, Team, and Enterprise users over the coming weeks. https://t.co/Fu2bgMChXt pic.twitter.com/M9AHLx5BKr — OpenAI (@OpenAI) May 16, 2024

OpenAI inks deal to train AI on Reddit data

OpenAI announced a partnership with Reddit that will give the company access to “real-time, structured and unique content” from the social network. Content from Reddit will be incorporated into ChatGPT, and the companies will work together to bring new AI-powered features to Reddit users and moderators.

We’re partnering with Reddit to bring its content to ChatGPT and new products: https://t.co/xHgBZ8ptOE — OpenAI (@OpenAI) May 16, 2024

OpenAI debuts GPT-4o “omni” model now powering ChatGPT

OpenAI’s spring update event saw the reveal of its new omni model, GPT-4o, which has a black hole-like interface , as well as voice and vision capabilities that feel eerily like something out of “Her.” GPT-4o is set to roll out “iteratively” across its developer and consumer-facing products over the next few weeks.

OpenAI demos real-time language translation with its latest GPT-4o model. pic.twitter.com/pXtHQ9mKGc — TechCrunch (@TechCrunch) May 13, 2024

OpenAI to build a tool that lets content creators opt out of AI training

The company announced it’s building a tool, Media Manager, that will allow creators to better control how their content is being used to train generative AI models — and give them an option to opt out. The goal is to have the new tool in place and ready to use by 2025.

OpenAI explores allowing AI porn

In a new peek behind the curtain of its AI’s secret instructions , OpenAI also released a new NSFW policy . Though it’s intended to start a conversation about how it might allow explicit images and text in its AI products, it raises questions about whether OpenAI — or any generative AI vendor — can be trusted to handle sensitive content ethically.

OpenAI and Stack Overflow announce partnership

In a new partnership, OpenAI will get access to developer platform Stack Overflow’s API and will get feedback from developers to improve the performance of their AI models. In return, OpenAI will include attributions to Stack Overflow in ChatGPT. However, the deal was not favorable to some Stack Overflow users — leading to some sabotaging their answer in protest .

U.S. newspapers file copyright lawsuit against OpenAI and Microsoft

Alden Global Capital-owned newspapers, including the New York Daily News, the Chicago Tribune, and the Denver Post, are suing OpenAI and Microsoft for copyright infringement. The lawsuit alleges that the companies stole millions of copyrighted articles “without permission and without payment” to bolster ChatGPT and Copilot.

OpenAI inks content licensing deal with Financial Times

OpenAI has partnered with another news publisher in Europe, London’s Financial Times , that the company will be paying for content access. “Through the partnership, ChatGPT users will be able to see select attributed summaries, quotes and rich links to FT journalism in response to relevant queries,” the FT wrote in a press release.

OpenAI opens Tokyo hub, adds GPT-4 model optimized for Japanese

OpenAI is opening a new office in Tokyo and has plans for a GPT-4 model optimized specifically for the Japanese language. The move underscores how OpenAI will likely need to localize its technology to different languages as it expands.

Sam Altman pitches ChatGPT Enterprise to Fortune 500 companies

According to Reuters, OpenAI’s Sam Altman hosted hundreds of executives from Fortune 500 companies across several cities in April, pitching versions of its AI services intended for corporate use.

OpenAI releases “more direct, less verbose” version of GPT-4 Turbo

Premium ChatGPT users — customers paying for ChatGPT Plus, Team or Enterprise — can now use an updated and enhanced version of GPT-4 Turbo . The new model brings with it improvements in writing, math, logical reasoning and coding, OpenAI claims, as well as a more up-to-date knowledge base.

Our new GPT-4 Turbo is now available to paid ChatGPT users. We’ve improved capabilities in writing, math, logical reasoning, and coding. Source: https://t.co/fjoXDCOnPr pic.twitter.com/I4fg4aDq1T — OpenAI (@OpenAI) April 12, 2024

ChatGPT no longer requires an account — but there’s a catch

You can now use ChatGPT without signing up for an account , but it won’t be quite the same experience. You won’t be able to save or share chats, use custom instructions, or other features associated with a persistent account. This version of ChatGPT will have “slightly more restrictive content policies,” according to OpenAI. When TechCrunch asked for more details, however, the response was unclear:

“The signed out experience will benefit from the existing safety mitigations that are already built into the model, such as refusing to generate harmful content. In addition to these existing mitigations, we are also implementing additional safeguards specifically designed to address other forms of content that may be inappropriate for a signed out experience,” a spokesperson said.

OpenAI’s chatbot store is filling up with spam

TechCrunch found that the OpenAI’s GPT Store is flooded with bizarre, potentially copyright-infringing GPTs . A cursory search pulls up GPTs that claim to generate art in the style of Disney and Marvel properties, but serve as little more than funnels to third-party paid services and advertise themselves as being able to bypass AI content detection tools.

The New York Times responds to OpenAI’s claims that it “hacked” ChatGPT for its copyright lawsuit

In a court filing opposing OpenAI’s motion to dismiss The New York Times’ lawsuit alleging copyright infringement, the newspaper asserted that “OpenAI’s attention-grabbing claim that The Times ‘hacked’ its products is as irrelevant as it is false.” The New York Times also claimed that some users of ChatGPT used the tool to bypass its paywalls.

OpenAI VP doesn’t say whether artists should be paid for training data

At a SXSW 2024 panel, Peter Deng, OpenAI’s VP of consumer product dodged a question on whether artists whose work was used to train generative AI models should be compensated . While OpenAI lets artists “opt out” of and remove their work from the datasets that the company uses to train its image-generating models, some artists have described the tool as onerous.

A new report estimates that ChatGPT uses more than half a million kilowatt-hours of electricity per day

ChatGPT’s environmental impact appears to be massive. According to a report from The New Yorker , ChatGPT uses an estimated 17,000 times the amount of electricity than the average U.S. household to respond to roughly 200 million requests each day.

ChatGPT can now read its answers aloud

OpenAI released a new Read Aloud feature for the web version of ChatGPT as well as the iOS and Android apps. The feature allows ChatGPT to read its responses to queries in one of five voice options and can speak 37 languages, according to the company. Read aloud is available on both GPT-4 and GPT-3.5 models.

ChatGPT can now read responses to you. On iOS or Android, tap and hold the message and then tap “Read Aloud”. We’ve also started rolling on web – click the "Read Aloud" button below the message. pic.twitter.com/KevIkgAFbG — OpenAI (@OpenAI) March 4, 2024

OpenAI partners with Dublin City Council to use GPT-4 for tourism

As part of a new partnership with OpenAI, the Dublin City Council will use GPT-4 to craft personalized itineraries for travelers, including recommendations of unique and cultural destinations, in an effort to support tourism across Europe.

A law firm used ChatGPT to justify a six-figure bill for legal services

New York-based law firm Cuddy Law was criticized by a judge for using ChatGPT to calculate their hourly billing rate . The firm submitted a $113,500 bill to the court, which was then halved by District Judge Paul Engelmayer, who called the figure “well above” reasonable demands.

ChatGPT experienced a bizarre bug for several hours

ChatGPT users found that ChatGPT was giving nonsensical answers for several hours , prompting OpenAI to investigate the issue. Incidents varied from repetitive phrases to confusing and incorrect answers to queries. The issue was resolved by OpenAI the following morning.

Match Group announced deal with OpenAI with a press release co-written by ChatGPT

The dating app giant home to Tinder, Match and OkCupid announced an enterprise agreement with OpenAI in an enthusiastic press release written with the help of ChatGPT . The AI tech will be used to help employees with work-related tasks and come as part of Match’s $20 million-plus bet on AI in 2024.

ChatGPT will now remember — and forget — things you tell it to

As part of a test, OpenAI began rolling out new “memory” controls for a small portion of ChatGPT free and paid users, with a broader rollout to follow. The controls let you tell ChatGPT explicitly to remember something, see what it remembers or turn off its memory altogether. Note that deleting a chat from chat history won’t erase ChatGPT’s or a custom GPT’s memories — you must delete the memory itself.

We’re testing ChatGPT's ability to remember things you discuss to make future chats more helpful. This feature is being rolled out to a small portion of Free and Plus users, and it's easy to turn on or off. https://t.co/1Tv355oa7V pic.twitter.com/BsFinBSTbs — OpenAI (@OpenAI) February 13, 2024

OpenAI begins rolling out “Temporary Chat” feature

Initially limited to a small subset of free and subscription users, Temporary Chat lets you have a dialogue with a blank slate. With Temporary Chat, ChatGPT won’t be aware of previous conversations or access memories but will follow custom instructions if they’re enabled.

But, OpenAI says it may keep a copy of Temporary Chat conversations for up to 30 days for “safety reasons.”

Use temporary chat for conversations in which you don’t want to use memory or appear in history. pic.twitter.com/H1U82zoXyC — OpenAI (@OpenAI) February 13, 2024

ChatGPT users can now invoke GPTs directly in chats

Paid users of ChatGPT can now bring GPTs into a conversation by typing “@” and selecting a GPT from the list. The chosen GPT will have an understanding of the full conversation, and different GPTs can be “tagged in” for different use cases and needs.

You can now bring GPTs into any conversation in ChatGPT – simply type @ and select the GPT. This allows you to add relevant GPTs with the full context of the conversation. pic.twitter.com/Pjn5uIy9NF — OpenAI (@OpenAI) January 30, 2024

ChatGPT is reportedly leaking usernames and passwords from users’ private conversations

Screenshots provided to Ars Technica found that ChatGPT is potentially leaking unpublished research papers, login credentials and private information from its users. An OpenAI representative told Ars Technica that the company was investigating the report.

ChatGPT is violating Europe’s privacy laws, Italian DPA tells OpenAI

OpenAI has been told it’s suspected of violating European Union privacy , following a multi-month investigation of ChatGPT by Italy’s data protection authority. Details of the draft findings haven’t been disclosed, but in a response, OpenAI said: “We want our AI to learn about the world, not about private individuals.”

OpenAI partners with Common Sense Media to collaborate on AI guidelines

In an effort to win the trust of parents and policymakers, OpenAI announced it’s partnering with Common Sense Media to collaborate on AI guidelines and education materials for parents, educators and young adults. The organization works to identify and minimize tech harms to young people and previously flagged ChatGPT as lacking in transparency and privacy .

OpenAI responds to Congressional Black Caucus about lack of diversity on its board

After a letter from the Congressional Black Caucus questioned the lack of diversity in OpenAI’s board, the company responded . The response, signed by CEO Sam Altman and Chairman of the Board Bret Taylor, said building a complete and diverse board was one of the company’s top priorities and that it was working with an executive search firm to assist it in finding talent. 

OpenAI drops prices and fixes ‘lazy’ GPT-4 that refused to work

In a blog post , OpenAI announced price drops for GPT-3.5’s API, with input prices dropping to 50% and output by 25%, to $0.0005 per thousand tokens in, and $0.0015 per thousand tokens out. GPT-4 Turbo also got a new preview model for API use, which includes an interesting fix that aims to reduce “laziness” that users have experienced.

Expanding the platform for @OpenAIDevs : new generation of embedding models, updated GPT-4 Turbo, and lower pricing on GPT-3.5 Turbo. https://t.co/7wzCLwB1ax — OpenAI (@OpenAI) January 25, 2024

OpenAI bans developer of a bot impersonating a presidential candidate

OpenAI has suspended AI startup Delphi, which developed a bot impersonating Rep. Dean Phillips (D-Minn.) to help bolster his presidential campaign. The ban comes just weeks after OpenAI published a plan to combat election misinformation, which listed “chatbots impersonating candidates” as against its policy.

OpenAI announces partnership with Arizona State University

Beginning in February, Arizona State University will have full access to ChatGPT’s Enterprise tier , which the university plans to use to build a personalized AI tutor, develop AI avatars, bolster their prompt engineering course and more. It marks OpenAI’s first partnership with a higher education institution.

Winner of a literary prize reveals around 5% her novel was written by ChatGPT

After receiving the prestigious Akutagawa Prize for her novel The Tokyo Tower of Sympathy, author Rie Kudan admitted that around 5% of the book quoted ChatGPT-generated sentences “verbatim.” Interestingly enough, the novel revolves around a futuristic world with a pervasive presence of AI.

Sam Altman teases video capabilities for ChatGPT and the release of GPT-5

In a conversation with Bill Gates on the Unconfuse Me podcast, Sam Altman confirmed an upcoming release of GPT-5 that will be “fully multimodal with speech, image, code, and video support.” Altman said users can expect to see GPT-5 drop sometime in 2024.

OpenAI announces team to build ‘crowdsourced’ governance ideas into its models

OpenAI is forming a Collective Alignment team of researchers and engineers to create a system for collecting and “encoding” public input on its models’ behaviors into OpenAI products and services. This comes as a part of OpenAI’s public program to award grants to fund experiments in setting up a “democratic process” for determining the rules AI systems follow.

OpenAI unveils plan to combat election misinformation

In a blog post, OpenAI announced users will not be allowed to build applications for political campaigning and lobbying until the company works out how effective their tools are for “personalized persuasion.”

Users will also be banned from creating chatbots that impersonate candidates or government institutions, and from using OpenAI tools to misrepresent the voting process or otherwise discourage voting.

The company is also testing out a tool that detects DALL-E generated images and will incorporate access to real-time news, with attribution, in ChatGPT.

Snapshot of how we’re preparing for 2024’s worldwide elections: • Working to prevent abuse, including misleading deepfakes • Providing transparency on AI-generated content • Improving access to authoritative voting information https://t.co/qsysYy5l0L — OpenAI (@OpenAI) January 15, 2024

OpenAI changes policy to allow military applications

In an unannounced update to its usage policy , OpenAI removed language previously prohibiting the use of its products for the purposes of “military and warfare.” In an additional statement, OpenAI confirmed that the language was changed in order to accommodate military customers and projects that do not violate their ban on efforts to use their tools to “harm people, develop weapons, for communications surveillance, or to injure others or destroy property.”

ChatGPT subscription aimed at small teams debuts

Aptly called ChatGPT Team , the new plan provides a dedicated workspace for teams of up to 149 people using ChatGPT as well as admin tools for team management. In addition to gaining access to GPT-4, GPT-4 with Vision and DALL-E3, ChatGPT Team lets teams build and share GPTs for their business needs.

OpenAI’s GPT store officially launches

After some back and forth over the last few months, OpenAI’s GPT Store is finally here . The feature lives in a new tab in the ChatGPT web client, and includes a range of GPTs developed both by OpenAI’s partners and the wider dev community.

To access the GPT Store, users must be subscribed to one of OpenAI’s premium ChatGPT plans — ChatGPT Plus, ChatGPT Enterprise or the newly launched ChatGPT Team.

the GPT store is live! https://t.co/AKg1mjlvo2 fun speculation last night about which GPTs will be doing the best by the end of today. — Sam Altman (@sama) January 10, 2024

Developing AI models would be “impossible” without copyrighted materials, OpenAI claims

Following a proposed ban on using news publications and books to train AI chatbots in the U.K., OpenAI submitted a plea to the House of Lords communications and digital committee. OpenAI argued that it would be “impossible” to train AI models without using copyrighted materials, and that they believe copyright law “does not forbid training.”

OpenAI claims The New York Times’ copyright lawsuit is without merit

OpenAI published a public response to The New York Times’s lawsuit against them and Microsoft for allegedly violating copyright law, claiming that the case is without merit.

In the response , OpenAI reiterates its view that training AI models using publicly available data from the web is fair use. It also makes the case that regurgitation is less likely to occur with training data from a single source and places the onus on users to “act responsibly.”

We build AI to empower people, including journalists. Our position on the @nytimes lawsuit: • Training is fair use, but we provide an opt-out • "Regurgitation" is a rare bug we're driving to zero • The New York Times is not telling the full story https://t.co/S6fSaDsfKb — OpenAI (@OpenAI) January 8, 2024

OpenAI’s app store for GPTs planned to launch next week

After being delayed in December , OpenAI plans to launch its GPT Store sometime in the coming week, according to an email viewed by TechCrunch. OpenAI says developers building GPTs will have to review the company’s updated usage policies and GPT brand guidelines to ensure their GPTs are compliant before they’re eligible for listing in the GPT Store. OpenAI’s update notably didn’t include any information on the expected monetization opportunities for developers listing their apps on the storefront.

GPT Store launching next week – OpenAI pic.twitter.com/I6mkZKtgZG — Manish Singh (@refsrc) January 4, 2024

OpenAI moves to shrink regulatory risk in EU around data privacy

In an email, OpenAI detailed an incoming update to its terms, including changing the OpenAI entity providing services to EEA and Swiss residents to OpenAI Ireland Limited. The move appears to be intended to shrink its regulatory risk in the European Union, where the company has been under scrutiny over ChatGPT’s impact on people’s privacy.

What is ChatGPT? How does it work?

ChatGPT is a general-purpose chatbot that uses artificial intelligence to generate text after a user enters a prompt, developed by tech startup OpenAI . The chatbot uses GPT-4, a large language model that uses deep learning to produce human-like text.

When did ChatGPT get released?

November 30, 2022 is when ChatGPT was released for public use.

What is the latest version of ChatGPT?

Both the free version of ChatGPT and the paid ChatGPT Plus are regularly updated with new GPT models. The most recent model is GPT-4o .

Can I use ChatGPT for free?

There is a free version of ChatGPT that only requires a sign-in in addition to the paid version, ChatGPT Plus .

Who uses ChatGPT?

Anyone can use ChatGPT! More and more tech companies and search engines are utilizing the chatbot to automate text or quickly answer user questions/concerns.

What companies use ChatGPT?

Multiple enterprises utilize ChatGPT, although others may limit the use of the AI-powered tool .

Most recently, Microsoft announced at it’s 2023 Build conference that it is integrating it ChatGPT-based Bing experience into Windows 11. A Brooklyn-based 3D display startup Looking Glass utilizes ChatGPT to produce holograms you can communicate with by using ChatGPT.  And nonprofit organization Solana officially integrated the chatbot into its network with a ChatGPT plug-in geared toward end users to help onboard into the web3 space.

What does GPT mean in ChatGPT?

GPT stands for Generative Pre-Trained Transformer.

What is the difference between ChatGPT and a chatbot?

A chatbot can be any software/system that holds dialogue with you/a person but doesn’t necessarily have to be AI-powered. For example, there are chatbots that are rules-based in the sense that they’ll give canned responses to questions.

ChatGPT is AI-powered and utilizes LLM technology to generate text after a prompt.

Can ChatGPT write essays?

Can chatgpt commit libel.

Due to the nature of how these models work , they don’t know or care whether something is true, only that it looks true. That’s a problem when you’re using it to do your homework, sure, but when it accuses you of a crime you didn’t commit, that may well at this point be libel.

We will see how handling troubling statements produced by ChatGPT will play out over the next few months as tech and legal experts attempt to tackle the fastest moving target in the industry.

Does ChatGPT have an app?

Yes, there is a free ChatGPT mobile app for iOS and Android users.

What is the ChatGPT character limit?

It’s not documented anywhere that ChatGPT has a character limit. However, users have noted that there are some character limitations after around 500 words.

Does ChatGPT have an API?

Yes, it was released March 1, 2023.

What are some sample everyday uses for ChatGPT?

Everyday examples include programing, scripts, email replies, listicles, blog ideas, summarization, etc.

What are some advanced uses for ChatGPT?

Advanced use examples include debugging code, programming languages, scientific concepts, complex problem solving, etc.

How good is ChatGPT at writing code?

It depends on the nature of the program. While ChatGPT can write workable Python code, it can’t necessarily program an entire app’s worth of code. That’s because ChatGPT lacks context awareness — in other words, the generated code isn’t always appropriate for the specific context in which it’s being used.

Can you save a ChatGPT chat?

Yes. OpenAI allows users to save chats in the ChatGPT interface, stored in the sidebar of the screen. There are no built-in sharing features yet.

Are there alternatives to ChatGPT?

Yes. There are multiple AI-powered chatbot competitors such as Together , Google’s Gemini and Anthropic’s Claude , and developers are creating open source alternatives .

How does ChatGPT handle data privacy?

OpenAI has said that individuals in “certain jurisdictions” (such as the EU) can object to the processing of their personal information by its AI models by filling out  this form . This includes the ability to make requests for deletion of AI-generated references about you. Although OpenAI notes it may not grant every request since it must balance privacy requests against freedom of expression “in accordance with applicable laws”.

The web form for making a deletion of data about you request is entitled “ OpenAI Personal Data Removal Request ”.

In its privacy policy, the ChatGPT maker makes a passing acknowledgement of the objection requirements attached to relying on “legitimate interest” (LI), pointing users towards more information about requesting an opt out — when it writes: “See here  for instructions on how you can opt out of our use of your information to train our models.”

What controversies have surrounded ChatGPT?

Recently, Discord announced that it had integrated OpenAI’s technology into its bot named Clyde where two users tricked Clyde into providing them with instructions for making the illegal drug methamphetamine (meth) and the incendiary mixture napalm.

An Australian mayor has publicly announced he may sue OpenAI for defamation due to ChatGPT’s false claims that he had served time in prison for bribery. This would be the first defamation lawsuit against the text-generating service.

CNET found itself in the midst of controversy after Futurism reported the publication was publishing articles under a mysterious byline completely generated by AI. The private equity company that owns CNET, Red Ventures, was accused of using ChatGPT for SEO farming, even if the information was incorrect.

Several major school systems and colleges, including New York City Public Schools , have banned ChatGPT from their networks and devices. They claim that the AI impedes the learning process by promoting plagiarism and misinformation, a claim that not every educator agrees with .

There have also been cases of ChatGPT accusing individuals of false crimes .

Where can I find examples of ChatGPT prompts?

Several marketplaces host and provide ChatGPT prompts, either for free or for a nominal fee. One is PromptBase . Another is ChatX . More launch every day.

Can ChatGPT be detected?

Poorly. Several tools claim to detect ChatGPT-generated text, but in our tests , they’re inconsistent at best.

Are ChatGPT chats public?

No. But OpenAI recently disclosed a bug, since fixed, that exposed the titles of some users’ conversations to other people on the service.

What lawsuits are there surrounding ChatGPT?

None specifically targeting ChatGPT. But OpenAI is involved in at least one lawsuit that has implications for AI systems trained on publicly available data, which would touch on ChatGPT.

Are there issues regarding plagiarism with ChatGPT?

Yes. Text-generating AI models like ChatGPT have a tendency to regurgitate content from their training data.

More TechCrunch

Get the industry’s biggest tech news, techcrunch daily news.

Every weekday and Sunday, you can get the best of TechCrunch’s coverage.

Startups Weekly

Startups are the core of TechCrunch, so get our best coverage delivered weekly.

TechCrunch Fintech

The latest Fintech news and analysis, delivered every Tuesday.

TechCrunch Mobility

TechCrunch Mobility is your destination for transportation news and insight.

Spain’s exposure to climate change helps Madrid-based VC, Seaya, close €300M climate-tech fund

According to a recent Dealroom report on the Spanish tech ecosystem, the combined enterprise value of Spanish startups surpassed €100 billion in 2023. In the latest confirmation of this upward trend, Madrid-based…

Forestay, Europe’s newest $220M growth-stage VC fund, will focus on AI

Forestay, an emerging VC based out of Geneva, Switzerland has been busy. This week it closed its second fund, Forestay Capital II, at a hard cap of $220 million. The…

A year later, what Threads could learn from other social networks

Threads, Meta’s alternative to Twitter, just celebrated its first birthday. After launching on July 5 last year, the social network has reached 175 million monthly active users — that’s a…

J2 Ventures, focused on military healthcare, grabs $150M for its second fund

J2 Ventures, a firm led mostly by U.S. military veterans, announced on Thursday that it has raised a $150 million second fund. The Boston-based firm invests in startups whose products…

HealthEquity says data breach is an ‘isolated incident’

HealthEquity said in an 8-K filing with the SEC that it detected “anomalous behavior by a personal use device belonging to a business partner.”

Roll20, an online tabletop role-playing game platform, discloses data breach

Roll20 said that on June 29 it had detected that a “bad actor” gained access to an account on the company’s administrative website for one hour.

Fisker asks bankruptcy court to sell its EVs at average of $14,000 each

Fisker has a willing buyer for its remaining inventory of all-electric Ocean SUVs, and has asked the Delaware Bankruptcy Court judge overseeing its Chapter 11 case to approve the sale.…

Fizz, the anonymous Gen Z social app, adds a marketplace for college students

Teddy Solomon just moved to a new house in Palo Alto, so he turned to the Stanford community on Fizz to furnish his room. “Every time I show up to…

Why deep tech VC Driving Forces is shutting down

With increasing competition for what is, essentially, still a small number of hard tech and deep tech deals, Sidney Scott realized it would be a challenge for smaller funds like…

How to turn off those silly video call reactions on iPhone and Mac

A guide to turn off reactions on your iPhone and Mac so you don’t get surprised by effects during work video calls.

Amazon retires its Astro for Business security robot after only 7 months

Amazon has decided to discontinue its Astro for Business device, a security robot for small- and medium-sized businesses, just seven months after launch.  In an email sent to customers and…

This Week in AI: With Chevron’s demise, AI regulation seems dead in the water

Hiya, folks, and welcome to TechCrunch’s regular AI newsletter. This week in AI, the U.S. Supreme Court struck down “Chevron deference,” a 40-year-old ruling on federal agencies’ power that required…

noplace, a mashup of Twitter and Myspace for Gen Z, hits No. 1 on the App Store

Noplace had already gone viral ahead of its public launch because of its feature that allows users to express themselves by customizing the colors of their profile.

Cloudflare launches a tool to combat AI bots

Cloudflare analyzed AI bot and crawler traffic to fine-tune automatic bot detection models.

Twilio says hackers identified cell phone numbers of two-factor app Authy users

Twilio says “threat actors were able to identify” phone numbers of people who use the two-factor app Authy.

Nano Dimension is buying Desktop Metal

The news brings closure to more than two years of volleying back and forth between some of the biggest names in additive manufacturing.

Groups save big at TechCrunch Disrupt 2024

Planning to attend TechCrunch Disrupt 2024 with your team? Maximize your team-building time and your company’s impact across the entire conference when you bring your team. Groups of 4 to…

Music video-sharing app Popster uses generative AI and lets artists remix videos

As more music streaming apps and creation tools emerge to compete for users’ attention, social music-sharing app Popster is getting two new features to grow its user base: an AI…

Threads nears its one-year anniversary with more than 175M monthly active users

Meta’s Threads now has more than 175 million monthly active users, Mark Zuckerberg announced on Wednesday. The announcement comes two days away from Threads’ first anniversary. Zuckerberg revealed back in…

From burritos to biotech: How robotics startup Cartken found its AV niche

Cartken and its diminutive sidewalk delivery robots first rolled into the world with a narrow charter: carrying everything from burritos and bento boxes to pizza and pad thai that last…

Granza Bio grabs $7M seed from Felicis and YC to advance delivery of cancer treatments

Ashwin Nandakumar and Ashwin Jainarayanan were working on their doctorates at adjacent departments in Oxford, but they didn’t know each other. Nandakumar, who was studying oncology, one day stumbled across…

LG acquires smart home platform Athom to bring third-party connectivity to its ThinQ ecosytem

LG has acquired an 80% stake in Athom, a Dutch smart home company and maker of the Homey smart home hub. According to LG’s announcement, it will purchase the remaining…

CoinDCX acquires BitOasis in international expansion push

CoinDCX, India’s leading cryptocurrency exchange, is expanding internationally through the acquisition of BitOasis, a digital asset platform in the Middle East and North Africa, the companies said Wednesday. The Bengaluru-based…

In a major update, Proton adds privacy-safe document collaboration to Drive, its freemium E2EE cloud storage service

Collaborative document features are being made available inside Proton Drive, further extending the company’s trademark pitch of robust security.

Telegram lets creators share paid content to channels

Telegram launched a digital currency called Stars for in-app use last month. Now, the company is expanding its use cases to paid content. The chat app is also allowing channels…

Altrove uses AI models and lab automation to create new materials

For the past couple of years, innovation has been accelerating in new materials development. And a new French startup called Altrove plans to play a role in this innovation cycle.…

Indian social network Koo is shutting down as buyout talks collapse

The Indian social media platform Koo, which positioned itself as a competitor to Elon Musk’s X, is ceasing operations after its last-resort acquisition talks with Dailyhunt collapsed. Despite securing over…

Europe is still serious about ESG, and Apiday is helping companies comply

Apiday leverages AI to save time for its customers. But like legacy consultants, it also offers human expertise.

Google’s environmental report pointedly avoids AI’s actual energy cost

Google totally dodges the question of how much energy is AI is using — perhaps because the answer is “way more than we’d care to say.”

SpaceX wants to launch up to 120 times a year from Florida — and competitors aren’t happy about it

SpaceX’s ambitious plans to launch its Starship mega-rocket up to 44 times per year from NASA’s Kennedy Space Center are causing a stir among some of its competitors. Late last…

Have a thesis expert improve your writing

Check your thesis for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• How to Write a Paper with ChatGPT | Tips & Examples

How to Write a Paper with ChatGPT | Tips & Examples

Published on 17 August 2023 by Koen Driessen .

A good research paper demonstrates your academic writing skills and knowledge of your chosen topic.

Your research paper should be based on in-depth independent research. However, generative AI tools like ChatGPT can be effectively used throughout the research process to:

• Brainstorm research questions
• Develop a methodology
• Create an outline
• Find sources
• Summarise and paraphrase text
• Provide feedback

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Brainstorming research questions, developing a methodology, creating an outline, finding sources, summarising or paraphrasing text, receiving feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to help formulate research questions , brainstorm potential thesis statements , or narrow down a broad subject area to a specific topic that interests you.

However, make sure that the outputs make sense and meet the requirements of your assignment. You can adapt these outputs manually, or use further prompts to ensure they meet your needs. For more information, see our tips for creating effective ChatGPT prompts .

• Generate three possible research questions for a research paper on the following topic: “The role of virtual reality in enhancing training and skill development in various industries.”
• “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods across different industries?”
• “How does the level of immersion in virtual reality training impact knowledge retention and skill transfer in fields such as medicine, aviation, and manufacturing?”
• “What are the key factors that influence the successful integration and adoption of virtual reality technology for training purposes in diverse industries, and what challenges hinder its widespread implementation?”

The only proofreading tool specialized in correcting academic writing

The academic proofreading tool has been trained on 1000s of academic texts and by native English editors. Making it the most accurate and reliable proofreading tool for students.

Correct my document today

Your paper should clearly indicate the data collection and analysis methods you used in your research.

You can use ChatGPT to help decide what kind of research you will conduct (e.g., qualitative or quantitative ), how you will analyse the data, and how you will mitigate potential research bias .

Bear in mind that you should be able to rationalize your chosen methodology . For example, you should ensure that it is either a standard methodology in the field or can be justified.

• Suggest three quantitative research methods appropriate to the following question: “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Experimental Study: Conduct a randomized controlled trial (RCT) where healthcare professionals are randomly assigned to either a virtual reality-based training group or a traditional training group. Both groups would receive training in specific healthcare tasks, and their cognitive and skill development outcomes would be measured and compared. Performance metrics, such as accuracy, speed, and efficiency, could be quantitatively assessed to determine the benefits of virtual reality-based training over traditional methods.
• Survey Research: Design a comprehensive survey targeting healthcare professionals who have undergone both virtual reality-based training and traditional training. The survey could include Likert-scale questions and structured response options to gauge their perceived cognitive and skill development benefits from each training method. Additionally, open-ended questions could be included to gather qualitative insights on specific strengths and weaknesses of each training approach.
• Task Performance Analysis: Implement a task-based assessment that simulates real-life healthcare scenarios, where participants are evaluated on their ability to handle critical situations. Participants would go through both virtual reality-based training and traditional training before being assessed in the simulated scenarios. Their performance in the assessment could be objectively measured using predefined criteria, allowing for a quantitative comparison of skill development between the two training methods.

A clear outline can help structure your paper, organise your arguments effectively, and make your research more efficient.

You can use generative AI tools like ChatGPT to formulate a potential outline to help guide your research. You can be as specific as you like, giving an overview of your research objectives , main arguments, and any evidence you intend to include in your paper.

However, ChatGPT outputs sometimes contain factual inaccuracies. It’s important to check the headings and subheadings suggested in the output and adapt them to meet your needs.

• Create an outline for an academic research paper with the following research question:“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?” The paper will be about 10 pages long.

B. Existing studies on cognitive and skill development benefits of virtual reality training

C. Comparison of virtual reality-based training with traditional training methods

D. Gaps in the literature and research limitations

III. Theoretical Framework

A. Theoretical basis for cognitive and skill development in training

B. Application of cognitive theories to virtual reality-based training

C. The role of immersive learning environments in skill acquisition

D. Conceptual framework for the study

IV. Research Methodology

A. Research design and approach (e.g., quasi-experimental, pre-post intervention)

B. Selection of participants and sample size calculation

C. Description of the virtual reality-based training and traditional training programs

D. Instruments and measures for assessing cognitive and skill development

E. Data collection procedures and ethical considerations

V. Data Analysis

A. Overview of statistical methods used for data analysis

B. Treatment of data and data cleaning

C. Quantitative analysis of cognitive and skill development outcomes

D. Presentation of findings with charts and tables

VI. Results

A. Presentation of the results of the cognitive and skill development assessments

B. Comparison of outcomes between virtual reality-based training and traditional training

C. Statistical significance and effect size analysis

D. Interpretation of the results and implications

VII. Discussion

A. Interpretation of findings in the context of the research question

B. Comparison of results with existing literature

C. Explanation of how virtual reality-based training impacts cognitive processes and skill development

D. Limitations of the study and areas for future research

VIII. Practical Implications

A. Practical applications of virtual reality-based training in healthcare settings

B. Recommendations for integrating virtual reality training in healthcare education

C. Benefits of virtual reality for continuous professional development in healthcare

IX. Conclusion

A. Summary of key findings

B. Reiteration of the research question and hypothesis

C. Contributions of the study to the field of healthcare training

D. Concluding remarks

X. References

You can use ChatGPT to help find sources relevant to your research. However, it’s important to be aware of the limitations of ChatGPT (for example, it occasionally cites nonexistent sources).

Instead of asking ChatGPT for specific source recommendations, try asking it for recommendations on the types of sources relevant to your research topic. You can also use it to generate a list of relevant keywords to use in your literature search.

• What types of sources could I use to write a research paper on the following research question? “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Academic Journals: Peer-reviewed journals are valuable sources of scholarly research. Look for articles in medical education, cognitive psychology, virtual reality applications in healthcare, and technology-enhanced learning.
• Research Studies: Seek out published research studies that specifically investigate the impact of virtual reality-based training on cognitive and skill development in healthcare professionals.
• Systematic Reviews and Meta-Analyses: These studies provide comprehensive overviews of existing research on a specific topic, making them a valuable source for summarizing and analyzing the overall evidence.
• Books and Book Chapters: Academic books and book chapters authored by experts in the fields of medical education, virtual reality, cognitive science, or instructional design can provide in-depth insights and theoretical foundations.
• Conference Proceedings: Proceedings from relevant conferences and symposiums may present the latest findings and advancements in virtual reality-based training and healthcare education.
• Educational Institution Websites: Universities and medical schools often publish research papers, case studies, and whitepapers related to medical education and virtual reality training.
• Industry Reports: Reports and whitepapers from healthcare organizations or technology companies exploring the benefits of virtual reality-based training in the healthcare sector.
• Government and Non-profit Organisations: Look for reports and publications from government agencies and non-profit organisations that focus on medical education and healthcare training.
• Online Databases: Utilize academic databases such as PubMed, Google Scholar, IEEE Xplore, and ScienceDirect to search for peer-reviewed research articles and conference papers.
• Expert Interviews: If possible, conduct interviews with experts in medical education, cognitive science, and virtual reality to gain valuable insights and perspectives.
• Surveys and Polls: Refer to reputable surveys and polls related to virtual reality-based training in the healthcare industry for additional statistical data.

You can use ChatGPT to paraphrase or summarise text. This can help you to condense sources to their most important points and explore new ways of expressing your ideas.

Alternatively you can use the more specialised tools featured on Scribbr’s AI writing resources page, which are designed specifically for these purposes and will give a smoother user experience.

• Provide a short summary of the following text:“One of the most profound applications of VR in healthcare is its use in surgical training. Traditionally, surgical training has relied on a combination of didactic lectures, observation of procedures, and hands-on experience in the operating room. However, these methods may not provide the ideal environment for novices to develop the necessary dexterity and spatial understanding essential for complex surgeries. VR overcomes these limitations by offering immersive, true-to-life simulations that allow surgeons to navigate through intricate anatomical structures, practice incisions, and learn to manage unexpected challenges that may arise during surgeries. This hands-on experience in a risk-free environment not only enhances technical skills but also builds confidence and reduces the learning curve for new surgical techniques.”
• Virtual Reality (VR) has a profound impact on healthcare, particularly in surgical training, as it provides immersive simulations that help surgeons develop dexterity, spatial understanding, and confidence for complex surgeries in a risk-free environment, ultimately enhancing their technical skills and reducing the learning curve.

When you’ve finished writing your research paper, you can use ChatGPT to receive feedback. You can be as specific as you like, selecting particular aspects the output should focus on (e.g., tone, clarity of structure, appropriateness of evidence to support your arguments).

You can also use ChatGPT to check grammar, spelling, and punctuation. However, it’s not designed for this purpose and occasionally misses errors. We recommend using a more specialised tool like Scribbr’s free grammar checker . Or, for more comprehensive feedback, Scribbr’s proofreading and editing service .

• Feedback the above text with regard to appropriateness of evidence and coherence of structure.
• The research paper demonstrates a well-structured and coherent presentation of the cognitive and skill development benefits of VR-based surgical training. The introduction effectively sets the context and rationale, while the literature review incorporates relevant historical and empirical evidence. The theoretical framework strengthens the foundation for the analysis.The methodology section could provide more details on the research design and study selection criteria. However, the sections on cognitive and skill development benefits present compelling evidence, supported by appropriate sub-sections.The exploration of improved patient outcomes lacks concrete examples but effectively outlines potential benefits. The section on challenges and future directions raises relevant points, but suggestions for solutions could enhance practicality.Overall, the paper combines theoretical, empirical, and practical evidence, offering a well-rounded approach. It establishes the significance of VR-based surgical training and concludes with a concise summary of key findings.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarise text . This can help you understand complex information more easily, summarise the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summariser , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialised tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, having ChatGPT write your college essay can negatively impact your application in numerous ways. ChatGPT outputs are unoriginal and lack personal insight.

Furthermore, Passing off AI-generated text as your own work is considered academically dishonest . AI detectors may be used to detect this offense, and it’s highly unlikely that any university will accept you if you are caught submitting an AI-generated admission essay.

However, you can use ChatGPT to help write your college essay during the preparation and revision stages (e.g., for brainstorming ideas and generating feedback).

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Driessen, K. (2023, August 17). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved 4 July 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, ethical implications of chatgpt, still have questions.

More From Forbes

7 chatgpt prompts to improve your writing.

• Share to Facebook
• Share to Twitter
• Share to Linkedin

Photo by NICOLAS MAETERLINCK/BELGA MAG/AFP via Getty Images

On writing , author David Sedaris once said, “You need to do the best that you can do, and then you need to take the best that you can do and you need to rewrite it, and rewrite it, and rewrite it.” That’s the dynamic essence of the writing process. Writers refine their drafts, just like they continually refine their craft. I didn’t study writing or literature, so I was intimidated when I began contributing to major publications. But my confidence grew with each byline, and I began to find my voice.

While ChatGPT can be an impressive imitator, it can never generate your unique voice and perspective. It can, however, be a powerful tool for improving your writing, whether you’re penning business articles or important emails. It all starts with the right prompts.

Here are seven that you can use to level up your writing skills.

Automate Your Busywork

There are no shortcuts to becoming a better writer. The prolific author Stephen King once said, “If you want to be a writer, you must do two things above all others: read a lot and write a lot.” That said, you can use AI tools to eliminate some of the tedious tasks involved in writing and leave more time for honing your craft. Here are some prompts to delegate your writing “busywork” to ChatGPT.

1. Generating Ideas And Topics

AI shouldn’t do your writing for you. It lacks the necessary human context and isn’t immune to errors. But it can be a powerful writing partner. As Wharton professor Christian Terwiesch (who challenged ChatGPT to come up with product ideas and compared those ideas to student ideas —ChatGPT won), has said , “Everybody should be using ChatGPT to help them generate ideas.” At worst, you reject all of them. At best, you enrich your pool of ideas.

Best High-Yield Savings Accounts Of 2024

Best 5% interest savings accounts of 2024.

Here is a prompt you can use to help get the idea wheels turning:

"I'm an [role/title] writing for [outlet description] targeting [target audience]. Can you suggest some fresh and engaging topics that would appeal to this audience?"

If you’d like ideas related to a certain topic or tailored to a specific style (e.g., a “hot take” versus a personal essay), remember: the more context you provide, the more concise the results.

2. Editing For Grammar And Style

Whether you’re sending an email or publishing an article on a high-traffic website, typos are an embarrassing—and avoidable—faux pas. In today’s world, where internet content exists in perpetuity, anything attached to your name should be error-free. ChatGPT can be a near-instantaneous proofreader. Test out the following prompt:

"Can you proofread this [content] for grammar, punctuation, and style consistency? The intended audience is [audience/recipient]. Please provide a list of any suggested improvements.”

3. Hitting The Right Tone

Spelling and grammar are a crucial part of editing, but they’re relatively objective. Perfecting the tone is more subjective and sometimes more challenging—but just as crucial.

The proper tone can ensure that your text is engaging. It can foster trust and understanding with colleagues and business partners. It can persuade your audience to get on board with your viewpoint. Writing that misses the mark on tone, however, can cause misunderstandings, hurt feelings, damage your credibility, and lose your reader’s interest.

With that in mind, here’s a prompt that can help you achieve the right tone in your writing:

"Can you help me rewrite this [content] for [audience], ensuring it maintains a [describe the desired tone]?

Add context to make ChatGPT’s reply more helpful. For example, if your content should show sensitivity to a certain issue or audience, add it to the prompt.

4. Adding Data And Research

One lesson I’ve learned from contributing to Forbes and other widely-read publications is that my word alone is rarely enough. I can share my personal experiences, but research and data can strengthen any piece of writing.

Instead of researching the traditional way—reviewing your writing and identifying facts that need outside sourcing, then Googling for relevant insight—ChatGPT can speed up the process, leaving you more time to polish those personal anecdotes. Try this prompt:

"I’m writing [describe the content and subject matter] for [target audience] and want to include relevant data and research. Can you review the following text and provide researched-backed statistics and insights on this topic?"

Importantly, always check the sources that ChatGPT generates. It will almost certainly come up with helpful results but they’re not always accurate—that’s where you, human editor, come into play.

Refine Your Craft

To continually improve your writing skills, you can take a page from the habits of professional writers. The following prompts can help you develop practices to become a stronger writer.

5. Daily Writing Prompts

I’ve written before about my morning pages . It’s a great way to clear my head before the day begins and to practice fluidly translating my thoughts into words on paper. If a blank page feels intimidating, writing prompts are a great way to get started. ChatGPT can generate writing prompts in an instant. You can keep it general:

“Can you suggest a couple of writing prompts that I can use to practice the craft of writing?”

Or, if you have a goal in mind, add more context. For example:

“I'm trying to improve engagement with my readers. Can you generate a couple of writing prompts to practice writing engaging content?”

6. Experiment With Different Styles And Voices

If you call your grandmother on the telephone, I’d bet your voice and speaking style sound vastly different from when you’re chatting with your best friend. Writing is the same.

ChatGPT can help you practice toggling between different styles and voices, and in doing so, help you find yours. You can ask ChatGPT for writing prompts to practice a certain style. For example:

“Can you generate three short exercises to help me practice writing in different voices and styles?”

ChatGPT will not only generate exercises, it will also break down the structure and elements of different writing styles and specify the tone.

Or, you can submit text to ChatGPT and ask it to analyze the style and voice. Try this prompt:

“Can you analyze the voice and style of the following text: [insert text].”

I used this prompt to assess the introduction to one of my recent Forbes stories, and ChatGPT said it was “Conversational and Relatable,” “Encouraging and Reassuring,” and “Informative and Practical”—encouraging feedback from my AI editor.

7. Rewrite, Rewrite, Rewrite

In A Moveable Feast , Ernest Hemingway wrote, “The only kind of writing is rewriting.”

If you want to become a writer, you have to embrace rewriting, whether you’re retyping every word or pouring over (and over) a Google Doc draft. Here are a couple of prompts you can use so that ChatGPT can assist in the rewriting process, one excerpt at a time:

“Rewrite this paragraph in the style of [Ernest Hemingway or any other author]."

“Rewrite this introduction so that it sounds like a story in [publication]”

“Rewrite this email so that it will resonate with [audience].”

“Rewrite this paragraph for clarity and concision.”

Importantly, ChatGPT only does part of the work. It falls to the writer to analyze the results, apply those lessons in future drafts, and, of course, to keep writing.

• Editorial Standards
• Reprints & Permissions

Join The Conversation

One Community. Many Voices. Create a free account to share your thoughts. 

Forbes Community Guidelines

Our community is about connecting people through open and thoughtful conversations. We want our readers to share their views and exchange ideas and facts in a safe space.

In order to do so, please follow the posting rules in our site's  Terms of Service.   We've summarized some of those key rules below. Simply put, keep it civil.

Your post will be rejected if we notice that it seems to contain:

• False or intentionally out-of-context or misleading information
• Insults, profanity, incoherent, obscene or inflammatory language or threats of any kind
• Attacks on the identity of other commenters or the article's author
• Content that otherwise violates our site's  terms.

User accounts will be blocked if we notice or believe that users are engaged in:

• Continuous attempts to re-post comments that have been previously moderated/rejected
• Racist, sexist, homophobic or other discriminatory comments
• Attempts or tactics that put the site security at risk
• Actions that otherwise violate our site's  terms.

So, how can you be a power user?

• Stay on topic and share your insights
• Feel free to be clear and thoughtful to get your point across
• ‘Like’ or ‘Dislike’ to show your point of view.
• Protect your community.
• Use the report tool to alert us when someone breaks the rules.

Thanks for reading our community guidelines. Please read the full list of posting rules found in our site's  Terms of Service.

14 ways to get better at using ChatGPT: Comprehensive prompt guide

• ChatGPT has taken the world by storm — but some struggle to get the chatbot to do what they want.
• Insider asked AI enthusiasts how they interact with the chatbot to produce desirable outputs.
• Here are 14 tips for crafting the best ChatGPT prompts, from assigning it a persona to being polite.

Since launching over a year ago, ChatGPT has become seemingly omnipresent.

At work, people have used the OpenAI product to develop code , generate marketing materials , and create lesson plans . It's become so popular that companies are now hiring workers who have ChatGPT expertise to boost their bottom lines. 

And in their everyday lives, people are turning to the chatbot for help with losing weight , landing dates , and delaying aging.

But ChatGPT doesn't always produce desirable outcomes, and the tech can be prone to errors and misinformation.

It all comes down to the prompts users put into ChatGPT. 

"If you really want to generate something that is going to be useful for you, you need to do more than just write a generic sentence," Jacqueline DeStefano-Tangorra, a consultant who uses ChatGPT to secure new contracts, told Insider . 

Insider sifted through AI research and asked AI enthusiasts, ChatGPT coaches, and workers who use the chatbot for tips on how to get ChatGPT to do what you want.

Here are 12 ways you can write better ChatGPT prompts. 

1. assign chatgpt a specific  role.

ChatGPT works best when you assign it a persona — such as a specific job role — Jason Gulya, an AI council chair at Berkeley College who teaches clients how to use ChatGPT, said.

Rob Cressy, the founder of the AI-coaching firm GPT Leaders, told Insider to "talk to ChatGPT like an employee" to help accomplish particular goals or tasks.

To do this, Gulya suggests that users write a prompt that includes a specific, concrete description of the persona you want the chatbot to take on. Begin your prompt with "act as a professor" or "act as a marketing professional," followed by a description of the desired outcome.

2. Be specific — and only give the bot one task at a time

Once you give ChatGPT a role, craft the prompt so it can accomplish a singular task such as writing a 300-word cover letter or generating a recipe for a protein-packed dinner.

"Don't ask it to do too much at once," Cressy said.

If you're a marketing professional, and you want ChatGPT to build a list of emails, Peggy Dean, an artist who runs a ChatGPT course for creatives , recommends crafting what she calls a "power prompt," a concise and detailed prompt.

If asking ChatGPT to brief a marketing campaign, she said she'd include target audiences, key features, and calls to action.

If asking the chatbot to come up with an email list and calls to action, she said she'd say:

"Pretend you are an expert email marketer and your client is a [role] specializing in [offerings] for [target audience]. Your goal is to build a robust email list in order to accomplish [goal]. Your client uses [platform(s)] to reach their audience. Come up with [details or quantity] ideal call to action ideas of [freebies or lead magnets] your client can provide."

"It's crucial to have a clear idea of what you hope to achieve," Dean told Insider. 

3. Refine your prompts based on a previous outputs

If ChatGPT's response isn't quite what you're looking for, Cressy said to build on its output by fine-tuning the initial prompt. He calls this process "peeling back an onion." 

"Don't be afraid to refine your prompts," DeStefano-Tangorra said. "If the initial output doesn't match your expectation, rephrase the prompt, add more detail, or clarify the context." 

If the answer to a prompt asking ChatGPT to "suggest a good book" is too vague, refine it to something like: "As someone who loves mystery novels with strong female leads, like Agatha Christie's Miss Marple series, can you suggest other similar books that I may enjoy?" 

4. Provide context 

ChatGPT prompts should include context such as historical information, user profiles, preferences, or any relevant details to guide its response, DeStefano-Tangorra said. The more specific, the better. 

Asking ChatGPT to "suggest dinner recipes," will lead to a generic output. Instead, DeStefano-Tangorra suggests tweaking that prompt to say: "As someone who loves trying out new cuisines and has a particular fondness of spicy food, can you suggest an exciting dinner menu for my next weekend get-together with my friends?"

If you want to apply ChatGPT to your business, Cressy suggests creating a "best-practices document" that includes details on who you are, what you do, and what your brand voice sounds like. That way, users can copy and paste the information into the chatbot whenever they start a new conversation. 

Instead of asking ChatGPT to "create me a marketing strategy" the prompt should say "I am a world-class [role] who helps [target audience] for business growth. Our brand voice is friendly, positive, inspiring, brand-safe, conversational. Create me a marketing strategy to help build my brand on Facebook and Instagram by leveraging my podcast." 

5. Break down the desired output into a series of steps

While it's best for prompts to be specific and include context, writing a long prompt can be counterproductive, Gulya said. 

"More often than not, a long mega-prompt does not give the desirable output," he said. 

Related stories

To avoid this, Gulya suggests breaking down the desired output into a series of steps. That way, if the chatbot generates errors, the user can pinpoint what exactly the chatbot may not understand. 

" This allows you to validate each step before proceeding, course-correcting when necessary," Gulya said. 

If the goal is to use ChatGPT to generate a widely read blog post, the user should ask the chatbot to first research which SEO terms will most likely make the article appear at the top of search-engine results. In a separate prompt, ask it to apply what it learned to the blog post.

6. Ask ChatGPT for advice on how to prompt it better 

To ensure your prompt is as thorough as it can be, Dean suggested asking ChatGPT what other details it needs from the user to produce the best output.

To do this, Dean suggests adding a line to your prompt that follows this template: "If I want to [desired outcome], what prompts should I share with ChatGPT in order to get the best results?" 

Once ChatGPT has generated an output, tell the chatbot what you like and dislike about the output and ask it to "request additional results, edits, or tweaks," she said.

7. Prioritize clarity and precision 

DeStefano-Tangorra suggests that ChatGPT users "explicitly outline your expectations within the prompt" by adding precise words. 

"Clear and specific prompts lead to more relevant and useful responses," she said. 

The prompt "compare and contrast using an oven versus a microwave for preparing dinner," should be tweaked to "can you compare and contrast the advantages and disadvantages of using a traditional oven versus a microwave for preparing a family dinner?" 

8. Use a thesaurus

To write your prompt with precision, Anna Bernstein, a prompt engineer at the generative-AI writing tool Copy.ai, suggests using a thesaurus to find the words that can increase your chances of getting what you want out of the chatbot. 

"Don't give up on a concept just because your first prompt didn't get the result you wanted," Bernstein previously told Insider . "Often, finding the right word or phrasing can unlock what you're doing."

9. Pay attention to verbs  

A thesaurus can help you find verbs that clearly express your intent. That way, the AI has a better chance of fully understanding your request, Bernstein said. 

She said that a prompt including the phrase "condense this" is stronger than "rewrite this to be shorter."

10. Be polite, but direct 

While ChatGPT users may have different conversational styles, Gulya said he finds that talking to the AI using polite, direct language — as if he's writing to a friend — yields the best results.

"Doing so puts me in a more collaborative, more flexible mindset," he said. 

When interacting with the chatbot for, say, advice on how college professors can enhance their skillsets, Gulya suggests writing flattering comments such as, "You're magnificent at seeing the root causes in faculty member's anxieties about artificial intelligence."

After the chatbot spits out a response you like, express gratitude by saying something like, "This is great. Thank you so much!" followed by a request to make revisions to its output.

11.Talk to ChatGPT with emotional language

If talking to ChatGPT like a friend doesn't produce desirable results, try adding some emotion to your prompts.  

A study conducted by a team of researchers from Microsoft, William & Mary, and research centers across Asia found that adding phrases like "This is very important to my career" and "You'd better be sure" to ChatGPT prompts yield better responses. 

ChatGPT users can also try writing prompts with phrases like "You'd better be sure," "Take pride in your work and give it your best," and "Remember that progress is made one step at a time. Stay determined and keep moving forward." 

12. Check and tweak the copy's tone and reading level 

If you're using ChatGPT to generate copy or captions for social media posts, make sure to tweak its tone so the content resonates with your target audience, Ashley Couto, a marketing professional who uses the chatbot to reduce her workload, told Business Insider.  

Couto finds that the best marketing copy reads at a fifth- or sixth-grade level, which includes "short sentences and paragraphs, a conversational tone, and simple language." 

To do this, Couto recommends asking ChatGPT to "change the reading level and tone" after it spits out a response. 

13. Feed ChatGPT an outline 

If you want ChatGPT to generate longer posts, Couto suggests giving the AI a specific structure and outline. She said the more specific you can be with your instructions, the better its output will be. 

Here's one prompt Couto uses to generate a company blog post:

"Following this story structure — 1. Capture the heart, 2. Set up a tension, 3. Resolve the tension, 4. Conclude by offering value — write a 1,000-word story at a grade-five reading level in the first person using the following information."

14. Include reference text 

Is ChatGPT making up answers that are factually incorrect? If so, adding bodies of text from trusted sources into the prompt may help eliminate these hallucinations. 

OpenAI's prompt guide suggests copying and pasting articles into ChatGPT, and then asking the chatbot to answer questions based on them.

An example of a prompt OpenAI provides is "Use the provided articles delimited by triple quotes to answer questions. If the answer cannot be found in the articles, write 'I could not find an answer.' After that, insert the text from the article below, followed by the questions you want ChatGPT to answer." 

What emotions did you feel while reading this article?

Select all that apply

Thanks for your input!

Watch: What is ChatGPT, and should we be afraid of AI chatbots?

• Main content