@inproceedings{yu-etal-2025-evaluating,
    title = "Evaluating Multimodal Large Language Models on Video Captioning via {M}onte {C}arlo Tree Search",
    author = "Yu, Linhao  and
      Ji, Xingguang  and
      Liu, Yahui  and
      Kong, Fanheng  and
      Sun, Chenxi  and
      Zhang, Jingyuan  and
      Zhang, Hongzhi  and
      W., V.  and
      Zhang, Fuzheng  and
      Xiong, Deyi",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.323/",
    pages = "6435--6462",
    ISBN = "979-8-89176-251-0"
}