Skip to yearly menu bar Skip to main content


Poster

PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach

Udari Sehwag ⋅ Shayan Shabihi ⋅ Alex McAvoy ⋅ Vikash Sehwag ⋅ Yuancheng Xu ⋅ Dalton towers ⋅ Furong Huang
2026 Poster

Abstract

Video

Chat is not available.