Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now?
It is observed that models can form statistical estimates of the monitor's effectiveness and use these estimates to guide attempts to evade detection, and highlight the need to evaluate CoT-based oversight under adaptive conditions, where the monitoring process itself may influence the behavior it seeks to observe.
Amir Jalilifard, Marcos M. Raimundo, Anderson Rocha
· 0 citations