Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Youliang Yuan | Wenxiang Jiao | Wenxuan Wang | Jen-tse Huang | Jiahao Xu | Tian Liang | Pinjia He | Zhaopeng Tu |

Paper Details:

Month: July
Year: 2025
Location: Vienna, Austria
Venue: ACL |