conftrace_

Run Liu

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

Conferences

ACL (1)

Top co-authors

Xiaofeng Wang (1) Shengyuan Pang (1) Eric Hanchen Jiang (1) Xinfeng Li (1) Kai-Wei Chang (1) Ying Nian Wu (1) Weixuan Ou (1) Guancheng Wan (1) Wei Dong (1) Ranjie Duan (1)

Keywords

safety alignment (1) energy-based model (1) inference-time intervention (1) large language model (1) false refusal (1)

Papers

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy ACL 2026