<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hutchinson-etal-2026-insight">
    <titleInfo>
        <title>InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maeve</namePart>
        <namePart type="family">Hutchinson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Syed</namePart>
        <namePart type="given">Mahbubul</namePart>
        <namePart type="family">Huq</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="family">Albinhassan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Radu</namePart>
        <namePart type="family">Jianu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aidan</namePart>
        <namePart type="family">Slingsby</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pranava</namePart>
        <namePart type="family">Madhyastha</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>Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic, requiring the active interrogation of interactive environments. Existing benchmarks are predominantly constrained to static imagery and one-shot question answering and fail to capture the epistemic demands of this domain, where evidence is frequently occluded, distributed across linked views, or conditionally revealed through user agency. In this paper, we introduce InSight, a benchmark for agentic claim verification over interactive visualizations. The dataset consists of 21,349 claims derived from human-authored analytical narratives and grounded in fully interactive web-based environments. Agents must navigate these environments to determine whether a natural language claim is supported, refuted or not verifiable given the available evidence. Unlike traditional evaluations, InSight treats interaction traces as intrinsic proxies for reasoning, enabling a rigorous audit of how models seek and synthesize visual evidence. We evaluate state-of-the-art models, revealing that interactive verification remains a non-trivial challenge. We release InSight at https://github.com/maevehutch/insight.</abstract>
    <identifier type="citekey">hutchinson-etal-2026-insight</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.606/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>13968</start>
            <end>13988</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations
%A Hutchinson, Maeve
%A Huq, Syed Mahbubul
%A Albinhassan, Mohammad
%A Jianu, Radu
%A Slingsby, Aidan
%A Madhyastha, Pranava
%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 hutchinson-etal-2026-insight
%X Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic, requiring the active interrogation of interactive environments. Existing benchmarks are predominantly constrained to static imagery and one-shot question answering and fail to capture the epistemic demands of this domain, where evidence is frequently occluded, distributed across linked views, or conditionally revealed through user agency. In this paper, we introduce InSight, a benchmark for agentic claim verification over interactive visualizations. The dataset consists of 21,349 claims derived from human-authored analytical narratives and grounded in fully interactive web-based environments. Agents must navigate these environments to determine whether a natural language claim is supported, refuted or not verifiable given the available evidence. Unlike traditional evaluations, InSight treats interaction traces as intrinsic proxies for reasoning, enabling a rigorous audit of how models seek and synthesize visual evidence. We evaluate state-of-the-art models, revealing that interactive verification remains a non-trivial challenge. We release InSight at https://github.com/maevehutch/insight.
%U https://aclanthology.org/2026.emnlp-main.606/
%P 13968-13988

Markdown (Informal)

[InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations](https://aclanthology.org/2026.emnlp-main.606/) (Hutchinson et al., EMNLP 2026)

• InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations (Hutchinson et al., EMNLP 2026)

ACL

• Maeve Hutchinson, Syed Mahbubul Huq, Mohammad Albinhassan, Radu Jianu, Aidan Slingsby, and Pranava Madhyastha. 2026. InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 13968–13988, Budapest, Hungary. Association for Computational Linguistics.