@inproceedings{laskar-etal-2026-lost,
    title = "Lost in Translation: Do {LVLM} Judges Generalize Across Languages?",
    author = "Laskar, Md Tahmid Rahman  and
      Islam, Mohammed Saidul  and
      Nayeem, Mir Tafseer  and
      Bhuiyan, Amran  and
      Rahman, Mizanur  and
      Joty, Shafiq  and
      Hoque, Enamul  and
      Huang, Jimmy",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1746/",
    pages = "34986--35002",
    ISBN = "979-8-89176-395-1",
    abstract = "Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision{--}language models (LVLMs). Despite their growing importance, these evaluators are almost exclusively assessed on English-centric benchmarks, leaving open the question of how well these evaluators generalize across languages. To answer this question, we introduce MM-JudgeBench, the first large-scale benchmark for multilingual and multimodal judge model evaluation, which includes over 60K pairwise preference instances spanning 25 typologically diverse languages. MM-JudgeBench integrates two complementary subsets: a general vision{--}language preference evaluation subset extending VL-RewardBench, and a chart-centric visual{--}text reasoning subset derived from OpenCQA, enabling systematic analysis of reward models (i.e., LVLM judges) across diverse settings. We additionally release a multilingual training set derived from MM-RewardBench, disjoint from our evaluation data, to support domain adaptation. By evaluating 22 LVLMs (15 open-source, 7 proprietary), we uncover substantial cross-lingual performance variance in our proposed benchmark. Our analysis further shows that model size and architecture are poor predictors of multilingual robustness, and that even state-of-the-art LVLM judges exhibit inconsistent behavior across languages. Together, these findings expose fundamental limitations of current reward modeling and underscore the necessity of multilingual, multimodal benchmarks for developing reliable automated evaluators."
}