@inproceedings{fan-etal-2025-language,
    title = "Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models",
    author = "Fan, Yuchun  and
      Wang, Yilin  and
      Mu, Yongyu  and
      Huang, Lei  and
      Li, Bei  and
      Feng, Xiaocheng  and
      Xiao, Tong  and
      Zhu, JingBo",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.666/",
    doi = "10.18653/v1/2025.findings-emnlp.666",
    pages = "12473--12500",
    ISBN = "979-8-89176-335-7",
    abstract = "Large vision-language models (LVLMs) have demonstrated exceptional capabilities in understanding visual information with human languages but also exhibit an imbalance in multilingual capabilities. In this work, we delve into the multilingual working pattern of LVLMs and identify a salient correlation between the multilingual understanding ability of LVLMs and language-specific neuron activations in shallow layers. Building on this insight, we introduce PLAST, a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise LAnguage Specific layers fine-Tuning. PLAST first identifies layers involved in multilingual understanding by monitoring language-specific neuron activations. These layers are then precisely fine-tuned with question-translation pairs to achieve multilingual alignment. Our empirical results on MMBench and MMMB demonstrate that PLAST effectively improves the multilingual capabilities of LVLMs and achieves significant efficiency with only 14{\%} of the parameters tuned. Further analysis reveals that PLAST facilitates the language-specific visual information engagement in shallow layers."
}