Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring
The theoretical and empirical results provide a holistic view of both the opportunities and the limitations of CoT monitoring, and show that the answer depends on the underlying task difficulty and the model size.
Mohammadali Mohammadkhani, M. Krishna, Yash Sarrof et al.
· 0 citations