conftrace_

Kai Qin

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

Conferences

ACL (1)

Top co-authors

Zhiyuan Sun (1) Daiting Shi (1) Houde Liu (1) Yu Liang (1) Wangyan (1) Long Xia (1) Liangxin Liu (1) Longzheng Wang (1) Zhang Yueyang (1)

Keywords

reinforcement learning from human feedback (1) preference modeling (1) positional bia (1) large language model (1) generative reward model (1)

Papers

ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework ACL 2026