Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis
Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of…
cs.AI2025
Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
Keertana Chidambaram, Karthik Vinary Seetharaman, Vasilis Syrgkanis
Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference…