@inproceedings{ming-etal-2026-one,
    title = "One-Token Rollout: Guiding Supervised Fine-Tuning of {LLM}s with Policy Gradient",
    author = "Ming, Rui  and
      Wu, Haoyuan  and
      Hu, Shoubo  and
      He, Zhuolun  and
      Yu, Bei",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1938/",
    doi = "10.18653/2026.findings-emnlp.1938",
    pages = "41341--41353",
    ISBN = "979-8-89176-462-0"
}