Enabling Scalable Evaluation of Unfair Patterns in Medical LLMs

Summary

Researchers present a generative method that uses knowledge graphs, medical ontologies and a base LLM to produce red-teaming evaluation cases for medical LLMs at scale. Each case flips a sensitive attribute, such as insurance status, to check whether the model's answer changes unfairly. The authors report that the generated cases are reliable and reveal bias patterns, and they publish a bias evaluation dataset on GitHub.