Hao Wang 0003, Yanting Wang, Hao Li 0031, Rui Li 0094, Lei Sha. Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay. 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 18700-18716, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.