<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-prismalign">
    <titleInfo>
        <title>PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Guangyi</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qianjun</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Boyu</namePart>
        <namePart type="family">Hou</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>Table extraction suffers from frequent structural errors and semantic hallucinations. We propose PrismAlign, a multi-VLM framework aligning diverse visual perspectives to resolve ambiguity. It integrates priors of table logic to assess output plausibility, decoupling structural alignment from cell content alignment. A Bayesian decision strategy maximizes alignment accuracy by exploiting the correlation between extraction errors and computable rule violations. Evaluated on open-source and custom VLMs, PrismAlign significantly reduces hallucinations and achieves state-of-the-art performance on OmniDocBench 1.5, as well as on the table category of CC-OCR and PureDocBench.</abstract>
    <identifier type="citekey">liu-etal-2026-prismalign</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.181/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>3069</start>
            <end>3078</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR
%A Liu, Guangyi
%A Huang, Qianjun
%A Hou, Boyu
%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 liu-etal-2026-prismalign
%X Table extraction suffers from frequent structural errors and semantic hallucinations. We propose PrismAlign, a multi-VLM framework aligning diverse visual perspectives to resolve ambiguity. It integrates priors of table logic to assess output plausibility, decoupling structural alignment from cell content alignment. A Bayesian decision strategy maximizes alignment accuracy by exploiting the correlation between extraction errors and computable rule violations. Evaluated on open-source and custom VLMs, PrismAlign significantly reduces hallucinations and achieves state-of-the-art performance on OmniDocBench 1.5, as well as on the table category of CC-OCR and PureDocBench.
%U https://aclanthology.org/2026.emnlp-industry.181/
%P 3069-3078

Markdown (Informal)

[PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR](https://aclanthology.org/2026.emnlp-industry.181/) (Liu et al., EMNLP 2026)

• PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR (Liu et al., EMNLP 2026)

ACL

• Guangyi Liu, Qianjun Huang, and Boyu Hou. 2026. PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 3069–3078, Budapest, Hungary. Association for Computational Linguistics.