@inproceedings{jiang-etal-2026-global,
    title = "Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation",
    author = "Jiang, Yubo  and
      Yang, Xin  and
      Wuerkaixi, Abudukelimu  and
      Yuan, Zheming  and
      Cheng, Xuxin  and
      Liu, Cao  and
      Zeng, Ke  and
      Xie, Fengying  and
      Jiang, Zhiguo  and
      Zhang, Haopeng",
    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.745/",
    pages = "15133--15152",
    ISBN = "979-8-89176-395-1",
    abstract = "Large vision{--}language models (LVLMs) excel at multimodal reasoning but still suffer from object-existence hallucinations when multi-step deliberation decouples from visual evidence. Think-with-Images (TwI) attempts to counter this by generating auxiliary observations (e.g., zoomed crops or highlighted views), yet it is not reliably beneficial. We identify two coupled failure modes: (1) a granularity{--}context trade-off of common operators, where zoom-in improves local detail but breaks global relations, while highlighting preserves topology but lacks fine evidence; and (2) an over-trust issue in tool-guided region proposals, where mislocalized evidence can dominate reasoning and even underperform standard prompting. We propose Active-Look, a training-free, plug-and-play TwI framework that allocates visual computation by uncertainty. Active-Look runs two heterogeneous grounding experts in parallel and uses their disagreement as a proxy for uncertainty, spending the budget only to verify disputed regions. It further mitigates the operator trade-off with conflict-aware hybrid rendering: highlighting retains global context, while selective zoom-in performs local verification. Experiments on hallucination-focused and general benchmarks (POPE, MME, and CHAIR) across multiple LVLM backbones show consistent gains."
}