3 papers
cs.AI2026
Measuring Reward-Seeking via Contrastive Belief Updates
Axel Højmark, Jérémy Scheurer, Evgenia Nitishinskaya +5
Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This "reward-seeking" is difficult to measure be…
cs.AI2025
Stress Testing Deliberative Alignment for Anti-Scheming Training
Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni +16
Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions,…
cs.LG2025
Trading Inference-Time Compute for Adversarial Robustness
Wojciech Zaremba, Evgenia Nitishinskaya, Boaz Barak +8
We conduct experiments on the impact of increasing inference-time compute in reasoning models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial attack…