<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2025-blinded">
    <titleInfo>
        <title>Blinded by Context: Unveiling the Halo Effect of MLLM in AI Hiring</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kyusik</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeongwoo</namePart>
        <namePart type="family">Ryu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hyeonseok</namePart>
        <namePart type="family">Jeon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bongwon</namePart>
        <namePart type="family">Suh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>This study investigates the halo effect in AI-driven hiring evaluations using Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Through experiments with hypothetical job applications, we examined how these models’ evaluations are influenced by non-job-related information, including extracurricular activities and social media images. By analyzing models’ responses to Likert-scale questions across different competency dimensions, we found that AI models exhibit significant halo effects, particularly in image-based evaluations, while text-based assessments showed more resistance to bias. The findings demonstrate that supplementary multimodal information can substantially influence AI hiring decisions, highlighting potential risks in AI-based recruitment systems.</abstract>
    <identifier type="citekey">kim-etal-2025-blinded</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.1338</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.1338/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>26067</start>
            <end>26113</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Blinded by Context: Unveiling the Halo Effect of MLLM in AI Hiring
%A Kim, Kyusik
%A Ryu, Jeongwoo
%A Jeon, Hyeonseok
%A Suh, Bongwon
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F kim-etal-2025-blinded
%X This study investigates the halo effect in AI-driven hiring evaluations using Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Through experiments with hypothetical job applications, we examined how these models’ evaluations are influenced by non-job-related information, including extracurricular activities and social media images. By analyzing models’ responses to Likert-scale questions across different competency dimensions, we found that AI models exhibit significant halo effects, particularly in image-based evaluations, while text-based assessments showed more resistance to bias. The findings demonstrate that supplementary multimodal information can substantially influence AI hiring decisions, highlighting potential risks in AI-based recruitment systems.
%R 10.18653/v1/2025.findings-acl.1338
%U https://aclanthology.org/2025.findings-acl.1338/
%U https://doi.org/10.18653/v1/2025.findings-acl.1338
%P 26067-26113

Markdown (Informal)

[Blinded by Context: Unveiling the Halo Effect of MLLM in AI Hiring](https://aclanthology.org/2025.findings-acl.1338/) (Kim et al., Findings 2025)

• Blinded by Context: Unveiling the Halo Effect of MLLM in AI Hiring (Kim et al., Findings 2025)

ACL

• Kyusik Kim, Jeongwoo Ryu, Hyeonseok Jeon, and Bongwon Suh. 2025. Blinded by Context: Unveiling the Halo Effect of MLLM in AI Hiring. In Findings of the Association for Computational Linguistics: ACL 2025, pages 26067–26113, Vienna, Austria. Association for Computational Linguistics.