@inproceedings{huo-etal-2026-sps,
    title = "{SPS}: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models",
    author = "Huo, Yifu  and
      Wang, Chenglong  and
      Zhu, Ziming  and
      Xing, Shunjie  and
      Feng, Peinan  and
      Liu, Tongran  and
      He, Qiaozhi  and
      Zhou, Tian Hua  and
      Changxiaojia  and
      Zhu, JingBo  and
      Yu, Zhengtao  and
      Xiao, Tong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.865/",
    pages = "17472--17489",
    ISBN = "979-8-89176-395-1"
}