Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring 事件

Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring arXiv:2502.05242v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain unclear. Chain-of-thoughts (CoTs) have been commonly utilized to externalize LLMs' thinking, but this strategy fails to accurately reflect LLMs' thinking process. Techniques based on LLMs' hidden representat