Implementing Large Language Models to Support Misconception-Based Collaborative Learning in Health Care Education

Abstract

This paper proposes a framework for leveraging large language models (LLMs) to generate misconceptions as a tool for collaborative learning in health care education. While misconceptions—particularly those generated by AI—are often viewed as detrimental to learning, we present an alternative perspective: that LLM-generated misconceptions, when addressed through structured peer discussion, can promote conceptual change and critical thinking. The paper outlines use cases across health care disciplines, including both clinical and basic science contexts, and a practical 10-step guidance for educators to implement the framework. It also highlights the need for medium- to long-term research to evaluate the impact of LLM-supported learning on student outcomes. This framework may support health care educators globally in integrating emerging AI technologies into their teaching, regardless of the disciplinary focus.