<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leite-etal-2026-llm-based">
    <titleInfo>
        <title>LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">João</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Leite</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Olesya</namePart>
        <namePart type="family">Razuvayevskaya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kalina</namePart>
        <namePart type="family">Bontcheva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carolina</namePart>
        <namePart type="family">Scarton</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>Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting noise or altering semantics, yet no existing framework exploits the adversarial potential of persuasion techniques against AFC systems, which are widely used in disinformation campaigns to manipulate audiences. In this paper, we introduce a novel class of persuasive adversarial attacks on AFCs by employing an LLM to rephrase claims using persuasion techniques. Considering 15 techniques grouped into 5 categories, we study the effects of persuasion on both claim verification and evidence retrieval using a decoupled evaluation strategy. Experiments on the FEVER and FEVEROUS benchmarks show that persuasion attacks can substantially degrade both verification performance and evidence retrieval. Our analysis identifies persuasion techniques as a potent class of adversarial attacks, highlighting the need for more robust AFC systems.</abstract>
    <identifier type="citekey">leite-etal-2026-llm-based</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.86/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2013</start>
            <end>2034</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
%A Leite, João A.
%A Razuvayevskaya, Olesya
%A Bontcheva, Kalina
%A Scarton, Carolina
%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 leite-etal-2026-llm-based
%X Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting noise or altering semantics, yet no existing framework exploits the adversarial potential of persuasion techniques against AFC systems, which are widely used in disinformation campaigns to manipulate audiences. In this paper, we introduce a novel class of persuasive adversarial attacks on AFCs by employing an LLM to rephrase claims using persuasion techniques. Considering 15 techniques grouped into 5 categories, we study the effects of persuasion on both claim verification and evidence retrieval using a decoupled evaluation strategy. Experiments on the FEVER and FEVEROUS benchmarks show that persuasion attacks can substantially degrade both verification performance and evidence retrieval. Our analysis identifies persuasion techniques as a potent class of adversarial attacks, highlighting the need for more robust AFC systems.
%U https://aclanthology.org/2026.emnlp-main.86/
%P 2013-2034

Markdown (Informal)

[LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems](https://aclanthology.org/2026.emnlp-main.86/) (Leite et al., EMNLP 2026)

• LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems (Leite et al., EMNLP 2026)

ACL

• João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, and Carolina Scarton. 2026. LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 2013–2034, Budapest, Hungary. Association for Computational Linguistics.