@inproceedings{zhu-etal-2026-wikiseeker,
    title = "{W}iki{S}eeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering",
    author = "Zhu, Yingjian  and
      Wang, Xinming  and
      Ding, Kun  and
      Wang, Ying  and
      Fan, Bin  and
      Xiang, Shiming",
    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.268/",
    pages = "5429--5449",
    ISBN = "979-8-89176-395-1"
}