@inproceedings{zhu-etal-2026-data,
    title = "Data Efficient {RLVR} via Off-Policy Influence Guidance",
    author = "Zhu, Erle  and
      Jiang, Dazhi  and
      Wang, Yuan  and
      Li, Xujun  and
      Cheng, Jiale  and
      Gu, Yuxian  and
      Niu, Yilin  and
      Zeng, Aohan  and
      Tang, Jie  and
      Huang, Minlie  and
      Wang, Hongning",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2141/",
    pages = "46167--46192",
    ISBN = "979-8-89176-390-6"
}