作者位次 #8/11ACL 2026Poster· Natural Language Processing
DUAL RM : Beyond Rule-based Preference Reward Modeling via Meta-Reward
Xiaobo Liang · Wanfu Wang · Qipeng Huang · Yuyang Ding · Zecheng Tang · Yixin Ji · Qianben Chen · Zhe Zhao · Kehai Chen · Juntao Li · Min Zhang
摘要
The ability to model sparse and underspecified rewards, characteristic of human preferences, is fundamental to scaling Reinforcement Learning (RL). Current preference-based reward modeling largely relies on verifiable rewards, where human-annotated labels define rule-based signals. However, these...