Tianyi Alex Qiu, Fanzhi Zeng, Jiaming Ji, Dong Yan, Kaile Wang, Jiayi Zhou, Yang Han, Josef Dai, Xuehai Pan, Yaodong Yang. Reward Generalization in RLHF: A Topological Perspective. In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar, editors, Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025. pages 15884-15930, Association for Computational Linguistics, 2025. [doi]
Abstract is missing.