<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-vision">
    <titleInfo>
        <title>Vision is Not Enough: Enhancing Bounding Box Grounding for Document Key Information Extraction with OCR Anchors</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhaochen</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rathika</namePart>
        <namePart type="given">Suresh</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Bai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhijie</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongxin</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Dahlmeier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Vision Language Model (VLM)-based OCR-free pipelines are increasingly adopted for industrial Key Information Extraction (KIE) systems due to their simpler end-to-end architecture and reduced dependence on potentially noisy OCR outputs. However, their reliability in grounding extracted values to precise bounding boxes remains unclear, raising questions about their suitability for grounding-critical use cases. In this paper, we present a systematic study of bounding box grounding capability in both general and document-specific VLMs. Our findings reveal a consistent extraction-grounding gap across model families. We revisit the OCR system as a grounding primitive and find that delegating the grounding step to Large Language Models (LLMs), rather than VLMs, in a zero-shot manner substantially improves region-level grounding accuracy. We introduce a fine-tuned 0.6B LLM that further improves the predicted box alignment, achieving high overlap with the target field for in-domain data while maintaining low serving latency. These results position OCR-anchored grounding as a practical deployment choice for industrial KIE systems that require both extraction and precise localization.</abstract>
    <identifier type="citekey">li-etal-2026-vision</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.184/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>3114</start>
            <end>3126</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Vision is Not Enough: Enhancing Bounding Box Grounding for Document Key Information Extraction with OCR Anchors
%A Li, Zhaochen
%A Kumar, Rathika Suresh
%A Bai, Tao
%A Zhang, Zhijie
%A Shao, Hongxin
%A Dahlmeier, Daniel
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F li-etal-2026-vision
%X Vision Language Model (VLM)-based OCR-free pipelines are increasingly adopted for industrial Key Information Extraction (KIE) systems due to their simpler end-to-end architecture and reduced dependence on potentially noisy OCR outputs. However, their reliability in grounding extracted values to precise bounding boxes remains unclear, raising questions about their suitability for grounding-critical use cases. In this paper, we present a systematic study of bounding box grounding capability in both general and document-specific VLMs. Our findings reveal a consistent extraction-grounding gap across model families. We revisit the OCR system as a grounding primitive and find that delegating the grounding step to Large Language Models (LLMs), rather than VLMs, in a zero-shot manner substantially improves region-level grounding accuracy. We introduce a fine-tuned 0.6B LLM that further improves the predicted box alignment, achieving high overlap with the target field for in-domain data while maintaining low serving latency. These results position OCR-anchored grounding as a practical deployment choice for industrial KIE systems that require both extraction and precise localization.
%U https://aclanthology.org/2026.emnlp-industry.184/
%P 3114-3126

Markdown (Informal)

[Vision is Not Enough: Enhancing Bounding Box Grounding for Document Key Information Extraction with OCR Anchors](https://aclanthology.org/2026.emnlp-industry.184/) (Li et al., EMNLP 2026)

• Vision is Not Enough: Enhancing Bounding Box Grounding for Document Key Information Extraction with OCR Anchors (Li et al., EMNLP 2026)

ACL

• Zhaochen Li, Rathika Suresh Kumar, Tao Bai, Zhijie Zhang, Hongxin Shao, and Daniel Dahlmeier. 2026. Vision is Not Enough: Enhancing Bounding Box Grounding for Document Key Information Extraction with OCR Anchors. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 3114–3126, Budapest, Hungary. Association for Computational Linguistics.