On the Risk of Misinformation Pollution with Large Language Models

@inproceedings{pan-etal-2023-risk,
    title = "On the Risk of Misinformation Pollution with Large Language Models",
    author = "Pan, Yikang  and
      Pan, Liangming  and
      Chen, Wenhu  and
      Nakov, Preslav  and
      Kan, Min-Yen  and
      Wang, William",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-emnlp.97",
    doi = "10.18653/v1/2023.findings-emnlp.97",
    pages = "1389--1403",
    abstract = "We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation and its subsequent impact on information-intensive applications, particularly Open-Domain Question Answering (ODQA) systems. We establish a threat model and simulate potential misuse scenarios, both unintentional and intentional, to assess the extent to which LLMs can be utilized to produce misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation (up to 87{\%}) in the performance of ODQA systems. Moreover, we uncover disparities in the attributes associated with persuading humans and machines, presenting an obstacle to current human-centric approaches to combat misinformation. To mitigate the harm caused by LLM-generated misinformation, we propose three defense strategies: misinformation detection, vigilant prompting, and reader ensemble. These approaches have demonstrated promising results, albeit with certain associated costs. Lastly, we discuss the practicality of utilizing LLMs as automatic misinformation generators and provide relevant resources and code to facilitate future research in this area.",
}

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-etal-2023-risk">
    <titleInfo>
        <title>On the Risk of Misinformation Pollution with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yikang</namePart>
        <namePart type="family">Pan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Liangming</namePart>
        <namePart type="family">Pan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenhu</namePart>
        <namePart type="family">Chen</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">Min-Yen</namePart>
        <namePart type="family">Kan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">William</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation and its subsequent impact on information-intensive applications, particularly Open-Domain Question Answering (ODQA) systems. We establish a threat model and simulate potential misuse scenarios, both unintentional and intentional, to assess the extent to which LLMs can be utilized to produce misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation (up to 87%) in the performance of ODQA systems. Moreover, we uncover disparities in the attributes associated with persuading humans and machines, presenting an obstacle to current human-centric approaches to combat misinformation. To mitigate the harm caused by LLM-generated misinformation, we propose three defense strategies: misinformation detection, vigilant prompting, and reader ensemble. These approaches have demonstrated promising results, albeit with certain associated costs. Lastly, we discuss the practicality of utilizing LLMs as automatic misinformation generators and provide relevant resources and code to facilitate future research in this area.</abstract>
    <identifier type="citekey">pan-etal-2023-risk</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.97</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.97</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>1389</start>
            <end>1403</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On the Risk of Misinformation Pollution with Large Language Models
%A Pan, Yikang
%A Pan, Liangming
%A Chen, Wenhu
%A Nakov, Preslav
%A Kan, Min-Yen
%A Wang, William
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F pan-etal-2023-risk
%X We investigate the potential misuse of modern Large Language Models (LLMs) for generating credible-sounding misinformation and its subsequent impact on information-intensive applications, particularly Open-Domain Question Answering (ODQA) systems. We establish a threat model and simulate potential misuse scenarios, both unintentional and intentional, to assess the extent to which LLMs can be utilized to produce misinformation. Our study reveals that LLMs can act as effective misinformation generators, leading to a significant degradation (up to 87%) in the performance of ODQA systems. Moreover, we uncover disparities in the attributes associated with persuading humans and machines, presenting an obstacle to current human-centric approaches to combat misinformation. To mitigate the harm caused by LLM-generated misinformation, we propose three defense strategies: misinformation detection, vigilant prompting, and reader ensemble. These approaches have demonstrated promising results, albeit with certain associated costs. Lastly, we discuss the practicality of utilizing LLMs as automatic misinformation generators and provide relevant resources and code to facilitate future research in this area.
%R 10.18653/v1/2023.findings-emnlp.97
%U https://aclanthology.org/2023.findings-emnlp.97
%U https://doi.org/10.18653/v1/2023.findings-emnlp.97
%P 1389-1403