Generative AI in educational processes: ChatGPT-4 in providing feedback to students’ written responses

Abstract

<p>This article examined the use of ChatGPT-4 in offering written feedback to students<br>regarding their open-ended responses in written exams. Proper feedback is crucial<br>for learning, helping students to understand their strengths, identify areas for<br>improvement, and devise strategies and practices for future learning. However,<br>crafting detailed and systematic feedback is a time-intensive task for teachers.<br>Consequently, there is growing interest in educational circles to leverage generative<br>AI and Large Language Models (LLMs) like ChatGPT for facilitating feedback<br>provision as part of adaptive learning environments. For this article, ChatGPT-4 was<br>employed to generate feedback for university students’ written exams. It<br>familiarized itself with evaluation guidelines, three short articles as learning<br>materials in English and related 54 student responses, which varied in length from<br>24 to 256 words in English. Then it evaluated these responses and provided each<br>student with personalized feedback that was on average 64 words long. The findings<br>suggest that ChatGPT-4 has the potential for providing systematic and constructive<br>feedback on students’ written exam responses. ChatGPT-4 need to be instructed<br>with precisely crafted prompts to ensure the feedback is precise and consistent and<br>aligns with teacher’s and educational institution’s objectives to support students in<br>learning.<br></p><p><br>Keywords: ChatGPT, Feedback, Education, Assessment, Generative AI<br></p>