MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming

Published in ACL 2025, 2025

arXiv | GitHub | PDF

Recommended citation: Weiyang Guo, Jing Li, Wenya Wang, Yu Li, Daojing He, Jun Yu, Min Zhang. (2025). "MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming." ACL 2025.
Download Paper