1
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
发现LLM推理稳定而响应存在不稳定性，利用这种不对称性来检测并缓解大模型的欺骗行为。
arXiv:2603.26846v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworth…