MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 26424-26442
Abstract
Weiyang Guo, Jing Li, Wenya Wang, Yu Li, Daojing He, Jun Yu, Min Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Jailbreaking Black Box Large Language Models in Twenty Queries2025
- Toward Optimal LLM Alignments Using Two-Player Games2025
- Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer2025
- PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference2025
- Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling2025
- Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts2024
- Knowledge Fusion By Evolving Weights of Language Models2024