@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",
    abstract = "Visual text grounding provides interpretable evidence for document question answering. Due to the complex layouts and mixed visual-text contents in text-rich images, effective visual text grounding requires strong visual and spatial reasoning to localize multiple referenced regions. Existing multimodal large language model (MLLM) approaches often struggle to align query tokens with visual{--}text patches, heavily relying on lengthy OCR inputs. To tackle this problem, we propose Doc-AGround, an OCR-free approach that leverages the MLLM{'}s inherent multi-head attention for multi-patch grounding. Doc-AGround extracts a patch-wise attention map as the grounding prediction. Concurrently, it introduces an effective multi-head weighting mechanism to amplify the attention heads' intrinsic role in connecting vision and text. Empirical results of Doc-AGround show state-of-the-art performance on challenging document grounding benchmarks, demonstrating the effectiveness of the proposed attention-based grounding design."
}