站内快照 · 国内可打开。外网原文可能无法访问。
- 论文公开站arXiv
Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be scaled up to frontier monitoring settings by collecting the largest deception dataset to date for train