<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="le-jeune-etal-2025-realharm">
    <titleInfo>
        <title>RealHarm: A Collection of Real-World Language Model Application Failures</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pierre</namePart>
        <namePart type="family">Le Jeune</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiaen</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luca</namePart>
        <namePart type="family">Rossi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matteo</namePart>
        <namePart type="family">Dora</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the The First Workshop on LLM Security (LLMSEC)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Leon</namePart>
            <namePart type="family">Derczynski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jekaterina</namePart>
            <namePart type="family">Novikova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Muhao</namePart>
            <namePart type="family">Chen</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">979-8-89176-279-4</identifier>
    </relatedItem>
    <abstract>Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses, empirical evidence of real-world failure modes remains underexplored. In this work, we introduce RealHarm, a dataset of annotated problematic interactions with AI agents built from a systematic review of publicly reported incidents. Analyzing harms, causes, and hazards specifically from the deployer’s perspective, we find that reputational damage constitutes the predominant organizational harm, while misinformation emerges as the most common hazard category. We empirically evaluate state-of-the-art guardrails and content moderation systems to probe whether such systems would have prevented the incidents, revealing a significant gap in the protection of AI applications.</abstract>
    <identifier type="citekey">le-jeune-etal-2025-realharm</identifier>
    <location>
        <url>https://aclanthology.org/2025.llmsec-1.7/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>87</start>
            <end>100</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RealHarm: A Collection of Real-World Language Model Application Failures
%A Le Jeune, Pierre
%A Liu, Jiaen
%A Rossi, Luca
%A Dora, Matteo
%Y Derczynski, Leon
%Y Novikova, Jekaterina
%Y Chen, Muhao
%S Proceedings of the The First Workshop on LLM Security (LLMSEC)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-279-4
%F le-jeune-etal-2025-realharm
%X Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses, empirical evidence of real-world failure modes remains underexplored. In this work, we introduce RealHarm, a dataset of annotated problematic interactions with AI agents built from a systematic review of publicly reported incidents. Analyzing harms, causes, and hazards specifically from the deployer’s perspective, we find that reputational damage constitutes the predominant organizational harm, while misinformation emerges as the most common hazard category. We empirically evaluate state-of-the-art guardrails and content moderation systems to probe whether such systems would have prevented the incidents, revealing a significant gap in the protection of AI applications.
%U https://aclanthology.org/2025.llmsec-1.7/
%P 87-100

Markdown (Informal)

[RealHarm: A Collection of Real-World Language Model Application Failures](https://aclanthology.org/2025.llmsec-1.7/) (Le Jeune et al., LLMSEC 2025)

• RealHarm: A Collection of Real-World Language Model Application Failures (Le Jeune et al., LLMSEC 2025)

ACL

• Pierre Le Jeune, Jiaen Liu, Luca Rossi, and Matteo Dora. 2025. RealHarm: A Collection of Real-World Language Model Application Failures. In Proceedings of the The First Workshop on LLM Security (LLMSEC), pages 87–100, Vienna, Austria. Association for Computational Linguistics.