AI Meets Mathematics Education: A Case Study on Supporting an Instructor in a Large Mathematics Class with Context-Aware AI

TL;DR

This case study explores a human-centered AI system supporting a large Calculus I class, demonstrating its effectiveness in answering student questions with high accuracy and positive student perception, emphasizing hybrid workflows.

Contribution

It presents a novel, human-centered AI support system for large courses, fine-tuned on historical interactions, with demonstrated accuracy and positive student feedback.

Findings

AI system achieved 75.3% accuracy on benchmark questions.

36% of AI responses rated equal or better than instructor answers.

Students valued response alignment and immediate availability.

Abstract

Large-enrollment university courses face persistent challenges in providing timely and scalable instructional support. While generative AI holds promise, its effective use depends on reliability and pedagogical alignment. We present a human-centered case study of AI-assisted support in a Calculus I course, implemented in close collaboration with the course instructor. We developed a system to answer students' questions on a discussion forum, fine-tuning a lightweight language model on 2,588 historical student-instructor interactions. The model achieved 75.3% accuracy on a benchmark of 150 representative questions annotated by five instructors, and in 36% of cases, its responses were rated equal to or better than instructor answers. Post-deployment student survey (N = 105) indicated that students valued the alignment of the responses with the course materials and their immediate availability, while still relying on the instructor verification for trust. We highlight the importance of hybrid human-AI workflows for safe and effective course support.