The Impact of Allowing ChatGPT on Responses to Different Question Types in a Mid-Term Math Exam

Bognár, László and Joós, Antal (2025) The Impact of Allowing ChatGPT on Responses to Different Question Types in a Mid-Term Math Exam. DUNAKAVICS, 13 (3). pp. 5-14. ISSN 2064-5007

Preview

Text 18621.pdf - Published Version Download (1MB) | Preview

Abstract

This study investigates the impact of ChatGPT on student performance in mid-term math exams, focusing on differences in scores across various types of test questions. The findings reveal that students using ChatGPT exhibited significantly lower average scores compared to their non-GPT counterparts, with more erratic performance patterns. In particular, ChatGPT users struggled with complex mathematical operations, such as matrix inverses and vector multiplications. Both ChatGPT and Copilot displayed similar levels of consistency, occasionally providing incorrect or mixed answers, which may have contributed to the lower performance of GPT users. The study suggests that inadequate preparation and unfamiliarity with using GPT during exams could also have played a role in these results. These findings raise important questions about the integration of AI tools in education, particularly in subjects like mathematics, where precision is essential. Future research should explore optimal ways to integrate AI tools like ChatGPT into learning environments to enhance, rather than hinder, academic performance.

Actions (login required)

Edit Item