@inproceedings{zhou-etal-2026-unveiling,
    title = "Unveiling Inherent Visual Grounding in Multimodal {LLM}s for Text-Rich Images",
    author = "Zhou, Shijie  and
      Kil, Jihyung  and
      Li, Ming  and
      Gu, Jiuxiang  and
      Wigington, Curtis  and
      Jain, Rajiv  and
      Chen, Changyou  and
      Zhang, Ruiyi",
    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.16/",
    pages = "352--370",
    ISBN = "979-8-89176-395-1"
}