Evaluating Anti-LGBTQIA+ Medical Bias in Large Language Models

    September 2025 in “ PLOS Digital Health
    Crystal Chang, Neha Srivathsa, Charbel Bou-Khalil, Akshay Swaminathan, Mitchell R. Lunn, K. Mishra, Oluwasanmi Koyejo, Roxana Daneshjou
    Image
    Studysummary This study found that all four evaluated large language models generated a significant proportion of inappropriate responses when prompted with or without LGBTQIA+ identity terms, with more severe bias observed in prompts mentioning LGBTQIA+ identities.
    Automatically generated from the study's abstract, not written by a person, and not a review of the full paper. Not medical advice or a treatment recommendation. Read the original study, and consult a qualified healthcare professional before changing treatment. Full disclaimer
    Discuss this study in the Community →

    Research cited in this study

    2 / 2 results