@inproceedings{zhang-etal-2026-mitigating,
    title = "Mitigating Exploration Bias in {RL} for Multi-Instruction Following",
    author = "Zhang, Mian  and
      Yin, Yueqin  and
      He, Kaiyu  and
      Wu, Peilin  and
      Zhang, Xinlu  and
      Zhou, Mingyuan  and
      Chen, Zhiyu",
    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.786/",
    pages = "16624--16633",
    ISBN = "979-8-89176-462-0"
}