<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bleick-etal-2024-german-voter">
    <titleInfo>
        <title>German Voter Personas Can Radicalize LLM Chatbots via the Echo Chamber Effect</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maximilian</namePart>
        <namePart type="family">Bleick</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nils</namePart>
        <namePart type="family">Feldhus</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aljoscha</namePart>
        <namePart type="family">Burchardt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sebastian</namePart>
        <namePart type="family">Möller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th International Natural Language Generation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saad</namePart>
            <namePart type="family">Mahamood</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nguyen</namePart>
            <namePart type="given">Le</namePart>
            <namePart type="family">Minh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daphne</namePart>
            <namePart type="family">Ippolito</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We investigate the impact of LLMs on political discourse with a particular focus on the influence of generated personas on model responses. We find an echo chamber effect from LLM chatbots when provided with German-language biographical information of politicians and voters in German politics, leading to sycophantic responses and the reinforcement of existing political biases. Findings reveal that personas of certain political party, such as those of the ‘Alternative für Deutschland’ party, exert a stronger influence on LLMs, potentially amplifying extremist views. Unlike prior studies, we cannot corroborate a tendency for larger models to exert stronger sycophantic behaviour. We propose that further development should aim at reducing sycophantic behaviour in LLMs across all sizes and diversifying language capabilities in LLMs to enhance inclusivity.</abstract>
    <identifier type="citekey">bleick-etal-2024-german-voter</identifier>
    <location>
        <url>https://aclanthology.org/2024.inlg-main.13</url>
    </location>
    <part>
        <date>2024-09</date>
        <extent unit="page">
            <start>153</start>
            <end>164</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T German Voter Personas Can Radicalize LLM Chatbots via the Echo Chamber Effect
%A Bleick, Maximilian
%A Feldhus, Nils
%A Burchardt, Aljoscha
%A Möller, Sebastian
%Y Mahamood, Saad
%Y Minh, Nguyen Le
%Y Ippolito, Daphne
%S Proceedings of the 17th International Natural Language Generation Conference
%D 2024
%8 September
%I Association for Computational Linguistics
%C Tokyo, Japan
%F bleick-etal-2024-german-voter
%X We investigate the impact of LLMs on political discourse with a particular focus on the influence of generated personas on model responses. We find an echo chamber effect from LLM chatbots when provided with German-language biographical information of politicians and voters in German politics, leading to sycophantic responses and the reinforcement of existing political biases. Findings reveal that personas of certain political party, such as those of the ‘Alternative für Deutschland’ party, exert a stronger influence on LLMs, potentially amplifying extremist views. Unlike prior studies, we cannot corroborate a tendency for larger models to exert stronger sycophantic behaviour. We propose that further development should aim at reducing sycophantic behaviour in LLMs across all sizes and diversifying language capabilities in LLMs to enhance inclusivity.
%U https://aclanthology.org/2024.inlg-main.13
%P 153-164

Markdown (Informal)

[German Voter Personas Can Radicalize LLM Chatbots via the Echo Chamber Effect](https://aclanthology.org/2024.inlg-main.13) (Bleick et al., INLG 2024)

• German Voter Personas Can Radicalize LLM Chatbots via the Echo Chamber Effect (Bleick et al., INLG 2024)

ACL

• Maximilian Bleick, Nils Feldhus, Aljoscha Burchardt, and Sebastian Möller. 2024. German Voter Personas Can Radicalize LLM Chatbots via the Echo Chamber Effect. In Proceedings of the 17th International Natural Language Generation Conference, pages 153–164, Tokyo, Japan. Association for Computational Linguistics.