@inproceedings{le-etal-2026-distribution,
    title = "When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift",
    author = "Le, Khoi M.  and
      Cao, Tri  and
      Nguyen, Phong Nam Huu  and
      Nguyen, Cong-Duy T  and
      Luu, Anh Tuan  and
      Miao, Chunyan  and
      Ng, See-Kiong  and
      Nguyen, Thong Thanh",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1240/",
    pages = "28270--28288",
    ISBN = "979-8-89176-459-0"
}