Sherpa: Teaching LLMs to Teach Adaptively
Presents novel RL training methodology for adaptive AI teaching systems with empirical results
AI Summary
Researchers introduce Sherpa, a reinforcement learning framework that trains LLMs to adaptively teach different student archetypes, improving learning outcomes by 20.5 percentage points.
Excerpt
Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approaches to training LLMs as teachers rely on demonstrations, preference data, or predefined pedagogical criteria that specify what good teaching looks like. However, these signals are often not grounded in individual student learning outcomes, where effective teaching strategies can vary substantially across learners. To address t