@inproceedings{jung-etal-2026-villain,
    title = "{VILLAIN} at {AV}er{I}ma{T}e{C}: Verifying Image{--}Text Claims via Multi-Agent Collaboration",
    author = "Jung, Jaeyoon  and
      Yoon, Yejun  and
      Yoon, Seunghyun  and
      Park, Kunwoo",
    editor = "Akhtar, Mubashara  and
      Aly, Rami  and
      Cao, Rui  and
      Christodoulopoulos, Christos  and
      Cocarascu, Oana  and
      Guo, Zhijiang  and
      Mittal, Arpit  and
      Schlichtkrull, Michael  and
      Thorne, James  and
      Vlachos, Andreas",
    booktitle = "Proceedings of the Ninth Fact Extraction and {VER}ification Workshop ({FEVER})",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ccl/2026.fever-1.9/",
    pages = "114--126",
    ISBN = "979-8-89176-365-4",
    abstract = "This paper describes VILLAIN, a multimodal fact-checking system that verifies image-text claims through prompt-based multi-agent collaboration. For the AVerImaTeC shared task, VILLAIN employs vision-language model agents across multiple stages of fact-checking. Textual and visual evidence is retrieved from the knowledge store enriched through additional web collection. To identify key information and address inconsistencies among evidence items, modality-specific and cross-modal agents generate analysis reports. In the subsequent stage, question-answer pairs are produced based on these reports. Finally, the Verdict Prediction agent produces the verification outcome based on the image-text claim and the generated question-answer pairs. Our system ranked first on the leaderboard across all evaluation metrics. The source code is publicly available at https://github.com/ssu-humane/VILLAIN."
}