• Using Role-Playing Scenarios to Identify Bias in LLMs

  • Sep 16 2024
  • Durée: 45 min
  • Podcast

Using Role-Playing Scenarios to Identify Bias in LLMs

  • Résumé

  • Harmful biases in large language models (LLMs) make AI less trustworthy and secure. Auditing for biases can help identify potential solutions and develop better guardrails to make AI safer. In this podcast from the Carnegie Mellon University Software Engineering Institute (SEI), Katie Robinson and Violet Turri, researchers in the SEI’s AI Division, discuss their recent work using role-playing game scenarios to identify biases in LLMs.

    Voir plus Voir moins

Ce que les auditeurs disent de Using Role-Playing Scenarios to Identify Bias in LLMs

Moyenne des évaluations de clients

Évaluations – Cliquez sur les onglets pour changer la source des évaluations.