<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="piper-jiang-2026-evaluating">
    <titleInfo>
        <title>Evaluating multi-modal LLMs on historical book illustrations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Piper</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiaming</namePart>
        <namePart type="family">Jiang</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Historical book illustrations are culturally significant multimodal artifacts that pose distinctive challenges for computational analysis, including sparse visual cues, historical reproduction techniques, and material degradation. We present the first task-specific evaluation of multimodal large language models (MLLMs) on historical book illustrations, testing five contemporary models on 1,969 children’s book illustrations across a range of visual labeling exercises and caption generation tasks. Frontier models performed strongly against human consensus annotations on concrete tasks, particularly illustration and setting detection, and mirrored human-level disagreement on entity, object and action identification. All model families struggled with accurate emotional intensity estimation. GPT and Gemini produced the strongest captions, with greater than 70% of images exhibiting no factual errors. Finally, frontier models closely recovered human distributions at the corpus level for major visual categories suggesting their appropriateness for use in large-scale studies.</abstract>
    <identifier type="citekey">piper-jiang-2026-evaluating</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1304</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1304/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>27575</start>
            <end>27589</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evaluating multi-modal LLMs on historical book illustrations
%A Piper, Andrew
%A Jiang, Jiaming
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F piper-jiang-2026-evaluating
%X Historical book illustrations are culturally significant multimodal artifacts that pose distinctive challenges for computational analysis, including sparse visual cues, historical reproduction techniques, and material degradation. We present the first task-specific evaluation of multimodal large language models (MLLMs) on historical book illustrations, testing five contemporary models on 1,969 children’s book illustrations across a range of visual labeling exercises and caption generation tasks. Frontier models performed strongly against human consensus annotations on concrete tasks, particularly illustration and setting detection, and mirrored human-level disagreement on entity, object and action identification. All model families struggled with accurate emotional intensity estimation. GPT and Gemini produced the strongest captions, with greater than 70% of images exhibiting no factual errors. Finally, frontier models closely recovered human distributions at the corpus level for major visual categories suggesting their appropriateness for use in large-scale studies.
%R 10.18653/2026.findings-emnlp.1304
%U https://aclanthology.org/2026.findings-emnlp.1304/
%U https://doi.org/10.18653/2026.findings-emnlp.1304
%P 27575-27589

Markdown (Informal)

[Evaluating multi-modal LLMs on historical book illustrations](https://aclanthology.org/2026.findings-emnlp.1304/) (Piper & Jiang, Findings 2026)

• Evaluating multi-modal LLMs on historical book illustrations (Piper & Jiang, Findings 2026)

ACL

• Andrew Piper and Jiaming Jiang. 2026. Evaluating multi-modal LLMs on historical book illustrations. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 27575–27589, Budapest, Hungary. Association for Computational Linguistics.