1
Value Drifts: Tracing Value Alignment During LLM Post-Training
追踪大模型后训练中价值对齐的动态变化，揭秘AI价值观漂移的关键时刻
arXiv:2510.26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted …