Towards Just-in-Time Adaptive Feedback: Enhancing Student Learning via Knowledge-Grounded LLM
For educators and students in large-scale courses, this framework offers a scalable method to deliver personalized, non-intrusive feedback that significantly enhances learning outcomes.
The paper presents a framework that uses LLMs grounded in domain-specific expert knowledge to provide just-in-time adaptive feedback in a large university course, improving student performance by over 80% compared to previous semesters.
Educational interventions are effective tools for enhancing student learning. While Large Language Models (LLMs) allow for generating adaptive feedback at scale, current studies lack clear methodologies for providing Just-in-Time (JiT) feedback in authentic instructional settings. In this paper, we present a framework that provides adaptive feedback by grounding LLMs with domain-specific expert knowledge. Our approach collects written reasoning logic (strategy essays) from students, analyzes potential error types based on the content of that reasoning, and delivers non-intrusive feedback designed to clarify missing or incorrect concepts. We deploy this framework in a large-scale university course (N > 1000), where it improved student performance by over 80% compared to previous semesters. Lastly, we validate the framework's pedagogical utility by analyzing the learning trajectories; we demonstrate how iterative conversations with LLM facilitate shifting one's misconception to correct understanding.