Page Content
Leveraging LLMs for Feedback Analysis
Building on emerging applications of AI in medical education, this work explores the use of large language models (LLMs) to analyze evaluations at scale. This initiative, developed in partnership with Education Reporting and Analytics, enables efficient synthesis of evaluation data at scale, helping programs uncover meaningful patterns, elevate learner voice, and accelerate continuous quality improvement efforts. Grounded in principles of rigorous evaluation and responsible AI, this work is designed to be adaptable across educational contexts. We invite collaborators across schools and programs interested in piloting or adapting this approach in their own evaluation contexts to connect with us.