GPTutor: A Generative AI-powered Intelligent Tutoring System to Support Interactive Learning with Knowledge-Grounded Question Answering
Richard Wing Cheung Lui, Haoran Bai, A. Ping Zhang, Elvin Tsun Him Chu · 2024
With increasing popularity of artificial intelligence (AI) in the education industry, intelligent tutoring system (ITS) powered by AI have been widely adopted to optimize the learning experience. However, the relationship between students’ engagement level of Generative AI (GenAI) and their academic performance is still under exploration. Also current popular GenAI products like ChatGPT suffer from the hallucination problem, which includes factuality, faithfulness, and maliciousness issues in the generated answer. This paper presents GPTutor, an ITS leveraging GenAI to support students' learning processes. GPTutor integrates a Retrieval-Augmented Generation (RAG) pipeline to deliver actual and contextually rich answers aligned to student questions and intended learning outcomes (ILO). A pilot evaluation involving undergraduate and postgraduate students assessed the system’s association with user experience, engagement, and academic performance. Results demonstrated that students generally recognize the effectiveness of GPTutor. Some students also provided insightful feedback on the benefits of GPTutor in improving learning efficiency and some limitations to be addressed. Notably, students with higher engagement levels showed significantly better academic performance on the final exam. This study proposed GPTutor to provide an interactive and knowledge-grounded learning experience and showed the strong association between students’ engagement in GPTutor and academic performance.