@inproceedings{li-etal-2025-transferring,
    title = "Transferring Textual Preferences to Vision-Language Understanding through Model Merging",
    author = "Li, Chen-An  and
      Lin, Tzu-Han  and
      Chen, Yun-Nung  and
      Lee, Hung-yi",
    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 2: Short Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.acl-short.72/",
    doi = "10.18653/v1/2025.acl-short.72",
    pages = "923--943",
    ISBN = "979-8-89176-252-7",
    abstract = "Large vision-language models (LVLMs) perform outstandingly across various multimodal tasks. However, their ability to evaluate generated content remains limited, and training vision-language reward models (VLRMs) with preference data is computationally expensive. This paper explores a training-free alternative by merging text-based reward models (RMs) with LVLMs to create VLRMs. Our approach shows that integrating these models leads to improved performance over LVLMs' scoring and text-based RMs, offering an efficient method for incorporating textual preferences into LVLMs."
}