<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mazumder-etal-2026-trust">
    <titleInfo>
        <title>To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Debajyoti</namePart>
        <namePart type="family">Mazumder</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mamta</namePart>
        <namePart type="family">Mamta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Abhirama</namePart>
        <namePart type="given">Subramanyam</namePart>
        <namePart type="family">Penamakuri</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VERISPEAK, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VERISPEAK contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text–speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim–evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VERISPEAK highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence.</abstract>
    <identifier type="citekey">mazumder-etal-2026-trust</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2534/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>57632</start>
            <end>57650</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech
%A Mazumder, Debajyoti
%A Mamta, Mamta
%A Penamakuri, Abhirama Subramanyam
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F mazumder-etal-2026-trust
%X Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VERISPEAK, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VERISPEAK contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text–speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim–evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VERISPEAK highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence.
%U https://aclanthology.org/2026.emnlp-main.2534/
%P 57632-57650

Markdown (Informal)

[To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech](https://aclanthology.org/2026.emnlp-main.2534/) (Mazumder et al., EMNLP 2026)

• To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech (Mazumder et al., EMNLP 2026)

ACL

• Debajyoti Mazumder, Mamta Mamta, and Abhirama Subramanyam Penamakuri. 2026. To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 57632–57650, Budapest, Hungary. Association for Computational Linguistics.