Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction.
Yuanbo Xie, Yingjie Zhang, Tianyun Liu, Duohe Ma, Tingwen Liu
Browse the full EMNLP paper archive.
Yuanbo Xie, Yingjie Zhang, Tianyun Liu, Duohe Ma, Tingwen Liu
Browse the full EMNLP paper archive.