@inproceedings{ye-etal-2026-dont,
    title = "Don{'}t Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free {RLVR}",
    author = "Ye, Yongshi  and
      Zhang, Liang  and
      Chen, Yidong  and
      Shi, Xiaodong  and
      Fu, Biao",
    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.2547/",
    doi = "10.18653/2026.emnlp-main.2547",
    pages = "57905--57928",
    ISBN = "979-8-89176-459-0"
}