Learning by Teaching: Engaging Students as Instructors of Large Language Models in Computer Science Education
This addresses a pedagogical challenge in computer science education by making learning more active and cost-effective.
The paper tackles the problem of passive learning and over-reliance on LLMs in computer science education by having students teach LLMs to solve problems, resulting in statistically significant improvements in student performance compared to historical cohorts.
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.