1
The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs
研究发现对齐训练并非消除文化知识，而是通过抑制机制在拒绝时刻压制模型内部logit分布。
arXiv:2510.13154v2 Announce Type: replace Abstract: What happens inside a language model when alignment training conflicts with a cultural value it en…