CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria.
Xinyu Hu, Yancheng He, Weixun Wang, Tao Feng, Li Lin, Jiashun Liu, Wenbo Su, Bo Zheng, Xiaojun Wan
Browse the full ACL paper archive.
Xinyu Hu, Yancheng He, Weixun Wang, Tao Feng, Li Lin, Jiashun Liu, Wenbo Su, Bo Zheng, Xiaojun Wan
Browse the full ACL paper archive.