<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cai-etal-2025-mhalo">
    <titleInfo>
        <title>MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yishuo</namePart>
        <namePart type="family">Cai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Renjie</namePart>
        <namePart type="family">Gu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiaxu</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xuancheng</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junzhe</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaotao</namePart>
        <namePart type="family">Gu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Minlie</namePart>
        <namePart type="family">Huang</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>Hallucination remains a critical challenge for multimodal large language models (MLLMs), undermining their reliability in real-world applications. While fine-grained hallucination detection (FHD) holds promise for enhancing high-quality vision-language data construction and model alignment through enriched feedback signals, automated solutions for this task have yet to be systematically explored. Inspired by the concept of “MLLM as a Judge”, we introduce MHALO, the first comprehensive benchmark specifically designed for evaluating MLLMs’ capability in performing token-level FHD. Our benchmark encompasses 12 distinct hallucination types spanning both multimodal perception and reasoning domains. Through extensive evaluations of 9 selected MLLMs, we reveal substantial performance limitations, with the leading model achieving an average F1_IoU of only 40.59%. To address this limitation, we develop HaloDet-4B, a specialized model trained on our curated training data, which significantly outperforms existing models. We hope the benchmark can provide valuable insights for future research on hallucination mitigation in MLLMs. The code and dataset will be publicly available.</abstract>
    <identifier type="citekey">cai-etal-2025-mhalo</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.478</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.478/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>9197</start>
            <end>9222</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors
%A Cai, Yishuo
%A Gu, Renjie
%A Li, Jiaxu
%A Huang, Xuancheng
%A Chen, Junzhe
%A Gu, Xiaotao
%A Huang, Minlie
%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 cai-etal-2025-mhalo
%X Hallucination remains a critical challenge for multimodal large language models (MLLMs), undermining their reliability in real-world applications. While fine-grained hallucination detection (FHD) holds promise for enhancing high-quality vision-language data construction and model alignment through enriched feedback signals, automated solutions for this task have yet to be systematically explored. Inspired by the concept of “MLLM as a Judge”, we introduce MHALO, the first comprehensive benchmark specifically designed for evaluating MLLMs’ capability in performing token-level FHD. Our benchmark encompasses 12 distinct hallucination types spanning both multimodal perception and reasoning domains. Through extensive evaluations of 9 selected MLLMs, we reveal substantial performance limitations, with the leading model achieving an average F1_IoU of only 40.59%. To address this limitation, we develop HaloDet-4B, a specialized model trained on our curated training data, which significantly outperforms existing models. We hope the benchmark can provide valuable insights for future research on hallucination mitigation in MLLMs. The code and dataset will be publicly available.
%R 10.18653/v1/2025.findings-acl.478
%U https://aclanthology.org/2025.findings-acl.478/
%U https://doi.org/10.18653/v1/2025.findings-acl.478
%P 9197-9222

Markdown (Informal)

[MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors](https://aclanthology.org/2025.findings-acl.478/) (Cai et al., Findings 2025)

• MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors (Cai et al., Findings 2025)

ACL

• Yishuo Cai, Renjie Gu, Jiaxu Li, Xuancheng Huang, Junzhe Chen, Xiaotao Gu, and Minlie Huang. 2025. MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors. In Findings of the Association for Computational Linguistics: ACL 2025, pages 9197–9222, Vienna, Austria. Association for Computational Linguistics.