<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alon-etal-2026-tabstructor">
    <titleInfo>
        <title>Tabstructor: Reconstructing Latent Borders in Borderless and Partially Ruled Tables</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alvin</namePart>
        <namePart type="given">Sarraga</namePart>
        <namePart type="family">Alon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniele</namePart>
        <namePart type="family">De Rosa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Johannes</namePart>
        <namePart type="family">Friedl</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Riza</namePart>
        <namePart type="family">Batista-Navarro</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>The Proceedings of Workshop on Document Intelligence and Understanding</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amit</namePart>
            <namePart type="family">Agarwal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Gupta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yova</namePart>
            <namePart type="family">Kementchedjhieva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aparna</namePart>
            <namePart type="family">Garimella</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yufang</namePart>
            <namePart type="family">Hou</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">979-8-89176-477-4</identifier>
    </relatedItem>
    <abstract>Borderless and partially ruled scientific tables often omit visual boundaries that mark logical rows, columns, and spanning regions. We introduce Tabstructor, a vision–language framework for latent-border reconstruction: predicting a table bounding box and horizontal and vertical segments representing logical boundaries even when visually absent or incomplete. On a held-out external test set, we compare task-specific prompting of a frozen base model, supervised fine-tuning, structure-preserving augmentation, and optional OCR-assisted geometry refinement. We introduce the Latent Border Reconstruction Score (LBRS; 0–100, higher is better) for evaluating valid structural and geometric border recovery. Task-specific prompting improves the frozen model, while fine-tuning provides the dominant gain, increasing LBRS from 38.552 to 90.014 (paired gain 51.462; 95% paired-bootstrap CI: 45.583–57.259). The augmented predictor reaches 93.487, a further 3.473-point gain, although it receives additional cumulative training exposure. OCR-assisted refinement improves boundary localisation and extent but adds only 0.467 points on average (95% CI: -1.968–2.615) and can cause boundary-count regressions. Thus, fine-tuning performs the principal reconstruction, while refinement is an optional, non-uniform geometry adjustment.</abstract>
    <identifier type="citekey">alon-etal-2026-tabstructor</identifier>
    <location>
        <url>https://aclanthology.org/2026.docinsights-1.18/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>244</start>
            <end>272</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Tabstructor: Reconstructing Latent Borders in Borderless and Partially Ruled Tables
%A Alon, Alvin Sarraga
%A De Rosa, Daniele
%A Friedl, Johannes
%A Batista-Navarro, Riza
%Y T.Y.S.S., Santosh
%Y Agarwal, Amit
%Y Gupta, Vivek
%Y Kementchedjhieva, Yova
%Y Garimella, Aparna
%Y Hou, Yufang
%S The Proceedings of Workshop on Document Intelligence and Understanding
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-477-4
%F alon-etal-2026-tabstructor
%X Borderless and partially ruled scientific tables often omit visual boundaries that mark logical rows, columns, and spanning regions. We introduce Tabstructor, a vision–language framework for latent-border reconstruction: predicting a table bounding box and horizontal and vertical segments representing logical boundaries even when visually absent or incomplete. On a held-out external test set, we compare task-specific prompting of a frozen base model, supervised fine-tuning, structure-preserving augmentation, and optional OCR-assisted geometry refinement. We introduce the Latent Border Reconstruction Score (LBRS; 0–100, higher is better) for evaluating valid structural and geometric border recovery. Task-specific prompting improves the frozen model, while fine-tuning provides the dominant gain, increasing LBRS from 38.552 to 90.014 (paired gain 51.462; 95% paired-bootstrap CI: 45.583–57.259). The augmented predictor reaches 93.487, a further 3.473-point gain, although it receives additional cumulative training exposure. OCR-assisted refinement improves boundary localisation and extent but adds only 0.467 points on average (95% CI: -1.968–2.615) and can cause boundary-count regressions. Thus, fine-tuning performs the principal reconstruction, while refinement is an optional, non-uniform geometry adjustment.
%U https://aclanthology.org/2026.docinsights-1.18/
%P 244-272

Markdown (Informal)

[Tabstructor: Reconstructing Latent Borders in Borderless and Partially Ruled Tables](https://aclanthology.org/2026.docinsights-1.18/) (Alon et al., DocInsights 2026)

• Tabstructor: Reconstructing Latent Borders in Borderless and Partially Ruled Tables (Alon et al., DocInsights 2026)

ACL

• Alvin Sarraga Alon, Daniele De Rosa, Johannes Friedl, and Riza Batista-Navarro. 2026. Tabstructor: Reconstructing Latent Borders in Borderless and Partially Ruled Tables. In The Proceedings of Workshop on Document Intelligence and Understanding, pages 244–272, Budapest, Hungary. Association for Computational Linguistics.