1
Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
用线性探针在LLM各层中间激活中提前解码拒绝行为，揭示安全机制的可预测性
arXiv:2605.28553v1 Announce Type: new Abstract: In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activati…