Generative AI platform delivers instant feedback in large math classes
Feedback Without the Wait: Piloting a Generative AI Practice Platform in a Large Maths Class
Artificial Intelligence
Summary
Getting quick and clear feedback helps students learn better, but in big math classes, it's hard for teachers to keep up and students can wait days to find out if they are on the right track. The authors created a tool using generative AI that gives students immediate clues and hints while they practice, without waiting for a teacher to check every answer right away. This system lets teachers check the solutions beforehand so the feedback students get is reliable. They tested how well students used the tool and whether they trusted its help.
What this means in practice
- •For online learning platform developers: Build immediate, AI-powered practice tools that give reliable hints during student exercises without needing real-time human grading.$Commercial implications: Enables AI-enhanced educational products that scale interactive feedback for large numbers of learners, improving user engagement and retention.
- •For technical training coordinators: Implement AI-based practice tools to provide learners with instant, step-by-step guidance in complex technical subjects without requiring constant instructor review.
Authors
Lili Chen, Gavin Buskes, Yuxin Ren, Chin Tong Leong
Abstract
Timely and specific feedback is one of the strongest influences on student learning, yet it is difficult to sustain in large electrical engineering classes where the ratio of students to demonstrators is high and a learner who is stuck may wait days to find out why an approach was wrong. Generative Artificial Intelligence (GenAI) offers a way to scale conversational feedback, but using it to grade assessed work raises trust and accountability concerns, and keeping a human in the loop to assure its judgements reintroduces the very delay that erodes the value of feedback. The result is a tension between the immediacy that makes feedback so impactful and the human oversight that makes it trustworthy. In this work, we set out to resolve that tension in practice by designing and piloting a GenAI practice platform that delivers immediate, scaffolded feedback during self-directed practice. This relocates human oversight from real-time grading to the upfront verification of solutions. Our goal was to understand how students engaged with the tool, how they perceived the value and reliability of its feedback, and what lessons transfer to other engineering subjects.