Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs 文章

ArXiv CS.AI2026-05-26NEWSen作者: Qitao Tan, Xiaoying Song, Arman Akbari, Arash Akbari, Yanzhi Wang, Xiaoming Zhai, Lingzi Hong, Zhen Xiang, Jin Lu, Geng Yuan
查看原文 →
关系图谱

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs · 相关技术

相关技术

TTEODELLMsafetydivide-and-conquer partitioningalignmentTEEStraight-Through EstimatorStanSULSAFEReferring expression comprehension (REC)Parts-of-Speech (POS) tagsPPROWSMITLMMHISFoundation ModelsForFOLFFIEffort Metric AttentionDAPTCISARGANNGit