Learning by Teaching: Engaging Students as Instructors of Large Language Models in Computer Science Education

TL;DR

This paper introduces a novel active-learning approach where students teach large language models in CS education, leading to improved student performance and engagement.

Contribution

It presents a new pedagogical paradigm and a system for students to teach LLMs, enhancing engagement and learning outcomes in CS education.

Findings

Students showed statistically significant performance improvements.

The method increased student engagement and mastery.

The approach is practical and cost-effective.

Abstract

While Large Language Models (LLMs) are often used as virtual tutors in computer science (CS) education, this approach can foster passive learning and over-reliance. This paper presents a novel pedagogical paradigm that inverts this model: students act as instructors who must teach an LLM to solve problems. To facilitate this, we developed strategies for designing questions with engineered knowledge gaps that only a student can bridge, and we introduce Socrates, a system for deploying this method with minimal overhead. We evaluated our approach in an undergraduate course and found that this active-learning method led to statistically significant improvements in student performance compared to historical cohorts. Our work demonstrates a practical, cost-effective framework for using LLMs to deepen student engagement and mastery.