<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bates-etal-2026-conspir">
    <titleInfo>
        <title>CONSPIR ED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Luke</namePart>
        <namePart type="family">Bates</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Max</namePart>
        <namePart type="family">Glockner</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Preslav</namePart>
        <namePart type="family">Nakov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Iryna</namePart>
        <namePart type="family">Gurevych</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Conspiracy theories erode public trust in science and institutions while resisting debunking by evolving and absorbing counter-evidence. As AI-generated misinformation becomes increasingly sophisticated, understanding the rhetorical patterns in conspiratorial content is important for developing interventions such as targeted prebunking and assessing AI vulnerabilities. We introduce CONSPIRED (CONSPIR Evaluation Dataset), which captures the cognitive traits of conspiratorial ideation in multi-sentence excerpts (80–120 words) from online conspiracy articles, annotated using the CONSPIR cognitive framework. CONSPIRED is the first dataset of conspiratorial content annotated for general cognitive traits. Using CONSPIRED, we (i) develop computational models that identify conspiratorial traits and the dominant trait in text excerpts, and (ii) evaluate LLM robustness to conspiratorial inputs. We find that LLMs are readily misaligned by conspiratorial framing, reproducing its rhetorical patterns even when successfully deflecting comparable fact-checked misinformation.1</abstract>
    <identifier type="citekey">bates-etal-2026-conspir</identifier>
    <identifier type="doi">10.1162/tacl.a.794</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.96/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>2120</start>
            <end>2144</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T CONSPIR ED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety
%A Bates, Luke
%A Glockner, Max
%A Nakov, Preslav
%A Gurevych, Iryna
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F bates-etal-2026-conspir
%X Conspiracy theories erode public trust in science and institutions while resisting debunking by evolving and absorbing counter-evidence. As AI-generated misinformation becomes increasingly sophisticated, understanding the rhetorical patterns in conspiratorial content is important for developing interventions such as targeted prebunking and assessing AI vulnerabilities. We introduce CONSPIRED (CONSPIR Evaluation Dataset), which captures the cognitive traits of conspiratorial ideation in multi-sentence excerpts (80–120 words) from online conspiracy articles, annotated using the CONSPIR cognitive framework. CONSPIRED is the first dataset of conspiratorial content annotated for general cognitive traits. Using CONSPIRED, we (i) develop computational models that identify conspiratorial traits and the dominant trait in text excerpts, and (ii) evaluate LLM robustness to conspiratorial inputs. We find that LLMs are readily misaligned by conspiratorial framing, reproducing its rhetorical patterns even when successfully deflecting comparable fact-checked misinformation.1
%R 10.1162/tacl.a.794
%U https://aclanthology.org/2026.tacl-1.96/
%U https://doi.org/10.1162/tacl.a.794
%P 2120-2144

Markdown (Informal)

[CONSPIR ED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety](https://aclanthology.org/2026.tacl-1.96/) (Bates et al., TACL 2026)

• CONSPIR ED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety (Bates et al., TACL 2026)

ACL

• Luke Bates, Max Glockner, Preslav Nakov, and Iryna Gurevych. 2026. CONSPIR ED: A Dataset for Cognitive Traits of Conspiracy Theories and Large Language Model Safety. Transactions of the Association for Computational Linguistics, 14:2120–2144.