Steering Away from Refusal: A Black-box Jailbreak Method Based on First-Token Distribution

Shuangjie Fu, Du Su, Xin Chen, Fei Sun 0002, Huawei Shen, Xueqi Cheng. Steering Away from Refusal: A Black-box Jailbreak Method Based on First-Token Distribution. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 25969-25979, Association for Computational Linguistics, 2026. [doi]

Authors

Shuangjie Fu

This author has not been identified. Look up 'Shuangjie Fu' in Google

Du Su

This author has not been identified. Look up 'Du Su' in Google

Xin Chen

This author has not been identified. Look up 'Xin Chen' in Google

Fei Sun 0002

This author has not been identified. Look up 'Fei Sun 0002' in Google

Huawei Shen

This author has not been identified. Look up 'Huawei Shen' in Google

Xueqi Cheng

This author has not been identified. Look up 'Xueqi Cheng' in Google