Shuangjie Fu, Du Su, Beining Huang, Fei Sun 0001, Jingang Wang, Wei Chen 0013, Huawei Shen, Xueqi Cheng. Jailbreak LLMs through Internal Stance Manipulation. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 15444-15459, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.