Episode Details

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.