<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2026-viscopilot">
    <titleInfo>
        <title>VisCopilot: Assisting Data-Driven Article Authoring with Fact-Based and Intent-Aligned Autocompletion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tzu-Wei</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Che-Wei</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Evelyn</namePart>
        <namePart type="given">Yi-Ting</namePart>
        <namePart type="family">Hung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jia-Yu</namePart>
        <namePart type="family">Pan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wen-Chieh</namePart>
        <namePart type="family">Lin</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</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Data-driven articles combine narrative text with visualizations to communicate insights but are time-consuming to produce, requiring both narrative composition and accurate text–chart linking. Existing automated linking methods struggle with accuracy, and automated narrative generation often misaligns with user intent and may contain hallucinations. We present VisCopilot, which leverages retrieval-augmented generation and large language models to provide fact-based, intent-aligned suggestions. As users write, the system supports narrative completion and text–chart linking in a single step, with a human-in-the-loop approach ensuring reliability. Technical evaluation on a benchmark dataset of data-driven articles authored by journalists confirmed the accuracy and quality of VisCopilot’s links. A user study further showed that VisCopilot outperforms baselines in usability, accuracy, and user confidence, with participants valuing its fact-based autocompletes for aligning suggestions with their writing intent. VisCopilot contributes: (1) an autocomplete-based design for assisting data-driven article authoring that balances efficiency, accuracy, and user autonomy; and (2) a reframing of text–chart link generation as a data-fact recommendation problem, enabling intent-aligned retrieval and systematic evaluation.</abstract>
    <identifier type="citekey">yu-etal-2026-viscopilot</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2301/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>52315</start>
            <end>52329</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VisCopilot: Assisting Data-Driven Article Authoring with Fact-Based and Intent-Aligned Autocompletion
%A Yu, Tzu-Wei
%A Chang, Che-Wei
%A Hung, Evelyn Yi-Ting
%A Pan, Jia-Yu
%A Lin, Wen-Chieh
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yu-etal-2026-viscopilot
%X Data-driven articles combine narrative text with visualizations to communicate insights but are time-consuming to produce, requiring both narrative composition and accurate text–chart linking. Existing automated linking methods struggle with accuracy, and automated narrative generation often misaligns with user intent and may contain hallucinations. We present VisCopilot, which leverages retrieval-augmented generation and large language models to provide fact-based, intent-aligned suggestions. As users write, the system supports narrative completion and text–chart linking in a single step, with a human-in-the-loop approach ensuring reliability. Technical evaluation on a benchmark dataset of data-driven articles authored by journalists confirmed the accuracy and quality of VisCopilot’s links. A user study further showed that VisCopilot outperforms baselines in usability, accuracy, and user confidence, with participants valuing its fact-based autocompletes for aligning suggestions with their writing intent. VisCopilot contributes: (1) an autocomplete-based design for assisting data-driven article authoring that balances efficiency, accuracy, and user autonomy; and (2) a reframing of text–chart link generation as a data-fact recommendation problem, enabling intent-aligned retrieval and systematic evaluation.
%U https://aclanthology.org/2026.emnlp-main.2301/
%P 52315-52329

Markdown (Informal)

[VisCopilot: Assisting Data-Driven Article Authoring with Fact-Based and Intent-Aligned Autocompletion](https://aclanthology.org/2026.emnlp-main.2301/) (Yu et al., EMNLP 2026)

• VisCopilot: Assisting Data-Driven Article Authoring with Fact-Based and Intent-Aligned Autocompletion (Yu et al., EMNLP 2026)

ACL

• Tzu-Wei Yu, Che-Wei Chang, Evelyn Yi-Ting Hung, Jia-Yu Pan, and Wen-Chieh Lin. 2026. VisCopilot: Assisting Data-Driven Article Authoring with Fact-Based and Intent-Aligned Autocompletion. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 52315–52329, Budapest, Hungary. Association for Computational Linguistics.