@inproceedings{ge-etal-2025-mllm,
    title = "{MLLM}-Bench: Evaluating Multimodal {LLM}s with Per-sample Criteria",
    author = "Ge, Wentao  and
      Chen, Shunian  and
      Chen, Guiming Hardy  and
      Chen, Nuo  and
      Chen, Junying  and
      Chen, Zhihong  and
      Xie, Wenya  and
      Yan, Shuo  and
      Zhu, Chenghao  and
      Lin, Ziyue  and
      Song, Dingjie  and
      Wang, Xidong  and
      Gao, Anningzhe  and
      Zhang, Zhiyi  and
      Li, Jianquan  and
      Wan, Xiang  and
      Wang, Benyou",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2025.naacl-long.256/",
    doi = "10.18653/v1/2025.naacl-long.256",
    pages = "4951--4974",
    ISBN = "979-8-89176-189-6"
}