<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2025-hallucination">
    <titleInfo>
        <title>Can Hallucination Correction Improve Video-Language Alignment?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lingjun</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mingyang</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Paola</namePart>
        <namePart type="family">Cascante-Bonilla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hal</namePart>
        <namePart type="given">Daumé</namePart>
        <namePart type="family">Iii</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kwonjoon</namePart>
        <namePart type="family">Lee</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>Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explore leveraging hallucination correction as a training objective to improve video-language alignment. We introduce HACA, a self-training framework learning to correct hallucinations in descriptions that do not align with the video content. By identifying and correcting inconsistencies, HACA enhances the model’s ability to align video and textual representations for spatio-temporal reasoning. Our experimental results show consistent gains in video-caption binding and text-to-video retrieval tasks, demonstrating that hallucination correction-inspired tasks serve as an effective strategy for improving vision and language alignment.</abstract>
    <identifier type="citekey">zhao-etal-2025-hallucination</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.1314</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.1314/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>25636</start>
            <end>25646</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Can Hallucination Correction Improve Video-Language Alignment?
%A Zhao, Lingjun
%A Xie, Mingyang
%A Cascante-Bonilla, Paola
%A Iii, Hal Daumé
%A Lee, Kwonjoon
%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 zhao-etal-2025-hallucination
%X Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explore leveraging hallucination correction as a training objective to improve video-language alignment. We introduce HACA, a self-training framework learning to correct hallucinations in descriptions that do not align with the video content. By identifying and correcting inconsistencies, HACA enhances the model’s ability to align video and textual representations for spatio-temporal reasoning. Our experimental results show consistent gains in video-caption binding and text-to-video retrieval tasks, demonstrating that hallucination correction-inspired tasks serve as an effective strategy for improving vision and language alignment.
%R 10.18653/v1/2025.findings-acl.1314
%U https://aclanthology.org/2025.findings-acl.1314/
%U https://doi.org/10.18653/v1/2025.findings-acl.1314
%P 25636-25646

Markdown (Informal)

[Can Hallucination Correction Improve Video-Language Alignment?](https://aclanthology.org/2025.findings-acl.1314/) (Zhao et al., Findings 2025)

• Can Hallucination Correction Improve Video-Language Alignment? (Zhao et al., Findings 2025)

ACL

• Lingjun Zhao, Mingyang Xie, Paola Cascante-Bonilla, Hal Daumé Iii, and Kwonjoon Lee. 2025. Can Hallucination Correction Improve Video-Language Alignment?. In Findings of the Association for Computational Linguistics: ACL 2025, pages 25636–25646, Vienna, Austria. Association for Computational Linguistics.