1
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
探索LLM欺骗探测线性探针的扩展性、鲁棒性与欺骗表示几何特性，为AI安全提供新视角。
arXiv:2605.27958v1 Announce Type: cross Abstract: Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, y…