Work

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

Year: 2025

Type: conference-paper

Abstract: Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Jiahao Xu, Tian Liang, Pinjia He, Zhaopeng Tu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2025.acl-long.158

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

Institutions: Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Tencent (China), Renmin University of China, Johns Hopkins University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Basic and Applied Basic Research Foundation of Guangdong Province

Award: G7609782405

OpenAlex ID: W4412886755

FWCI: 6.886

Cites:

Cited by: 7

Related to: 10