Researchers designed a framework for improving the quality, equity, and fairness of large language models used for mental health support. AI chatbots can detect race, but racial bias reduces response empathy.

Researchers at MIT, NYU, and UCLA develop an approach to help evaluate whether large language models like GPT-4 are equitable enough to be clinically viable for mental health support.

  • rumba@lemmy.zipEnglish
    3·
    2 days ago

    The problem with using GPT as it is currently, you can ask it the same question 27 tomes and get 18 different answers. One of them a hallucination.