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.
arxiv 2024
Selected/Recent Publications
GPT-4 Is Too Smart To Be Safe Stealthy Chat with LLMs via Cipher
Youliang Yuan; Wenxiang Jiao; Wenxuan Wang; Jen-tse Huang; Pinjia He; Shuming Shi; Zhaopeng Tu.
ICLR 2024
Does ChatGPT Know that It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT
Youliang Yuan, Wenxuan Wang, Qingshuo Guo, Yiming Xiong, Chihao Shen and Pinjia He
COLING 2024 (Oral)
Projects
: DeRTa
Complete list: [Google Scholar]