conftrace_
← Authors

Tongxin Liu

1 papers · 2026–2026 · 1 conference · across top CS/AI conferences

Conferences

ACL (1)

Top co-authors

Duohe Ma (1) Jianfeng Si (1) Xiangzheng Zhang (1) Xiaokun Yuan (1) Kaiqi Guan (1) Jiawen Tao (1) Zhewen Tan (1) Lin Sun (1) Wenhan Yu (1) Huiyan Jin (1)

Keywords

reinforcement learning (1) safety alignment (1) adversarial prompt generation (1) large language model (1)

Papers

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment ACL 2026