New Study: ChatGPT Outperforms University Students in Writing

Artificial Intelligence Keyboard

ChatGPT scored similarly or better than university students in 9 out of 32 courses when answering assessment questions, according to a study involving NYUAD. Although 74% of surveyed students across five countries would use ChatGPT, 70% of educators view its use as plagiarism.

A recent study published in Scientific Reports suggests that ChatGPT’s performance in responding to examination questions in various disciplines such as computer science, politics, engineering, and psychology, may be comparable to, or even surpass, the average university student’s performance. Additionally, the study revealed that nearly 75% of the students surveyed expressed willingness to use ChatGPT for assistance with their assignments, notwithstanding the perception of many educators that utilizing ChatGPT amounts to plagiarism.

To investigate how ChatGPT performed when writing university assessments compared to students, Talal Rahwan and Yasir Zaki invited faculty members who taught different courses at New York University Abu Dhabi (NYUAD) to provide three student submissions each for ten assessment questions that they had set.

ChatGPT was then asked to produce three sets of answers to the ten questions, which were then assessed alongside student-written answers by three graders (who were unaware of the source of the answers). The ChatGPT-generated answers achieved a similar or higher average grade than students in 9 of 32 courses. Only mathematics and economics courses saw students consistently outperform ChatGPT. ChatGPT outperformed students most markedly in the ‘Introduction to Public Policy’ course, where its average grade was 9.56 compared to 4.39 for students.

The authors also surveyed views on whether ChatGPT could be used to assist with university assignments among 1,601 individuals from Brazil, India, Japan, the US, and the UK (including at least 200 students and 100 educators from each country). 74 percent of students indicated that they would use ChatGPT in their work. In contrast, in all countries, educators underestimated the proportion of students who plan to use ChatGPT and 70 percent of educators reported that they would treat its use as plagiarism.

Finally, the authors report that two tools for identifying AI-generated text — GPTZero and AI text classifier — misclassified the ChatGPT answers generated in this research as written by a human 32 percent and 49 percent of the time respectively.

Together, these findings offer insights that could inform policy for the use of AI tools within educational settings.

Reference: “Perception, performance, and detectability of conversational artificial intelligence across 32 university courses” by Hazem Ibrahim, Fengyuan Liu, Rohail Asim, Balaraju Battu, Sidahmed Benabderrahmane, Bashar Alhafni, Wifag Adnan, Tuka Alhanai, Bedoor AlShebli, Riyadh Baghdadi, Jocelyn J. Bélanger, Elena Beretta, Kemal Celik, Moumena Chaqfeh, Mohammed F. Daqaq, Zaynab El Bernoussi, Daryl Fougnie, Borja Garcia de Soto, Alberto Gandolfi, Andras Gyorgy, Nizar Habash, J. Andrew Harris, Aaron Kaufman, Lefteris Kirousis, Korhan Kocak, Kangsan Lee, Seungah S. Lee, Samreen Malik, Michail Maniatakos, David Melcher, Azzam Mourad, Minsu Park, Mahmoud Rasras, Alicja Reuben, Dania Zantout, Nancy W. Gleason, Kinga Makovi, Talal Rahwan and Yasir Zaki, 24 August 2023, Scientific Reports.
DOI: 10.1038/s41598-023-38964-3

1 Comment on "New Study: ChatGPT Outperforms University Students in Writing"

  1. However, ChatGPT doesn’t know when it is blowing smoke!

    Perhaps a good test for the origin of the writing is the number of factual errors in the text.

Leave a comment

Email address is optional. If provided, your email will not be published or shared.