作者位次 #5/7ICLR 2026Poster· Social Aspects / Trustworthy Machine Learning
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