Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling

Xiaoyu Liu, Di Liang, Hongyu Shan, Peiyang Liu, Yonghao Liu 0001, Muling Wu, Yuntao Li, Xianjie Wu, Li Miao, Jiangrong Shen, Minlong Peng. Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling. In Saloni Potdar, Lina Maria Rojas-Barahona, Sébastien Montella, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025 - Industry Track, Suzhou, China, November 4-9, 2025. pages 672-685, Association for Computational Linguistics, 2025. [doi]

Abstract

Abstract is missing.