@inproceedings{huang-etal-2025-mmevalpro,
    title = "{MME}val{P}ro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation",
    author = "Huang, Jinsheng  and
      Chen, Liang  and
      Guo, Taian  and
      Zeng, Fu  and
      Zhao, Yusheng  and
      Wu, Bohan  and
      Yuan, Ye  and
      Zhao, Haozhe  and
      Guo, Zhihui  and
      Zhang, Yichi  and
      Yuan, Jingyang  and
      Ju, Wei  and
      Liu, Luchen  and
      Liu, Tianyu  and
      Chang, Baobao  and
      Zhang, Ming",
    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-2025-COMPUTEL/2025.naacl-long.247/",
    pages = "4805--4822",
    ISBN = "979-8-89176-189-6"
}