<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2025-comparison">
    <titleInfo>
        <title>Comparison of AI and Human Scoring on A Visual Arts Assessment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ning</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Joshua</namePart>
            <namePart type="family">Wilson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Ormerod</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Magdalen</namePart>
            <namePart type="family">Beiting Parrish</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>National Council on Measurement in Education (NCME)</publisher>
            <place>
                <placeTerm type="text">Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-218-84229-1</identifier>
    </relatedItem>
    <abstract>This study examines reliability and comparability of Generative AI scores versus human ratings on two performance tasks—text-based and drawing-based—in a fourth-grade visual arts assessment. Results show GPT-4 is consistent, aligned with humans but more lenient, and its agreement with humans is slightly lower than that between human raters.</abstract>
    <identifier type="citekey">jiang-etal-2025-comparison</identifier>
    <location>
        <url>https://aclanthology.org/2025.aimecon-wip.18/</url>
    </location>
    <part>
        <date>2025-10</date>
        <extent unit="page">
            <start>147</start>
            <end>154</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comparison of AI and Human Scoring on A Visual Arts Assessment
%A Jiang, Ning
%A Huang, Yue
%A Chen, Jie
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84229-1
%F jiang-etal-2025-comparison
%X This study examines reliability and comparability of Generative AI scores versus human ratings on two performance tasks—text-based and drawing-based—in a fourth-grade visual arts assessment. Results show GPT-4 is consistent, aligned with humans but more lenient, and its agreement with humans is slightly lower than that between human raters.
%U https://aclanthology.org/2025.aimecon-wip.18/
%P 147-154

Markdown (Informal)

[Comparison of AI and Human Scoring on A Visual Arts Assessment](https://aclanthology.org/2025.aimecon-wip.18/) (Jiang et al., AIME-Con 2025)

• Comparison of AI and Human Scoring on A Visual Arts Assessment (Jiang et al., AIME-Con 2025)

ACL

• Ning Jiang, Yue Huang, and Jie Chen. 2025. Comparison of AI and Human Scoring on A Visual Arts Assessment. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress, pages 147–154, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).