@inproceedings{he-etal-2025-rewarding,
    title = "Rewarding the Unlikely: Lifting {GRPO} Beyond Distribution Sharpening",
    author = "He, Andre Wang  and
      Fried, Daniel  and
      Welleck, Sean",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1298/",
    pages = "25559--25571",
    ISBN = "979-8-89176-332-6"
}