Evaluating reasoning LLMs’ potential to perpetuate racial and gender disease stereotypes in healthcare
Journal:
medRxiv
Published Date:
Jan 1, 2025
Abstract
This evaluation of 36,000 clinical vignettes found that next-generation reasoning large language models, o3-mini and DeepSeek-R1, frequently perpetuate racial and gender stereotypes for common medical conditions, indicating that advancements in reasoning do not inherently improve representational fairness.
