Li, J., Wen, X., Ma, Z., Hu, S., Zhang, Q., & Wang, Z. (2026). Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment.
Chicago Style (17th ed.) CitationLi, Jiajia, Xiaoyu Wen, Zhongtian Ma, Shuyue Hu, Qiaosheng Zhang, and Zhen Wang. Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment. 2026.
MLA (9th ed.) CitationLi, Jiajia, et al. Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment. 2026.
Warning: These citations may not always be 100% accurate.