<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chalkidis-2024-investigating">
    <titleInfo>
        <title>Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ilias</namePart>
        <namePart type="family">Chalkidis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</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">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In light of the recent 2024 European Parliament elections, we are investigating if LLMs can be used as Voting Advice Applications (VAAs). We audit MISTRAL and MIXTRAL models and evaluate their accuracy in predicting the stance of political parties based on the latest “EU and I” voting assistance questionnaire. Furthermore, we explore alternatives to improve models’ performance by augmenting the input context via Retrieval-Augmented Generation (RAG) relying on web search, and Self-Reflection using staged conversations that aim to re-collect relevant content from the model’s internal memory. We find that MIXTRAL is highly accurate with an 82% accuracy on average with a significant performance disparity across different political groups (50-95%). Augmenting the input context with expert-curated information can lead to a significant boost of approx. 9%, which remains an open challenge for automated RAG approaches, even considering curated content.</abstract>
    <identifier type="citekey">chalkidis-2024-investigating</identifier>
    <identifier type="doi">10.18653/v1/2024.emnlp-main.312</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.312</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>5455</start>
            <end>5467</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024
%A Chalkidis, Ilias
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F chalkidis-2024-investigating
%X In light of the recent 2024 European Parliament elections, we are investigating if LLMs can be used as Voting Advice Applications (VAAs). We audit MISTRAL and MIXTRAL models and evaluate their accuracy in predicting the stance of political parties based on the latest “EU and I” voting assistance questionnaire. Furthermore, we explore alternatives to improve models’ performance by augmenting the input context via Retrieval-Augmented Generation (RAG) relying on web search, and Self-Reflection using staged conversations that aim to re-collect relevant content from the model’s internal memory. We find that MIXTRAL is highly accurate with an 82% accuracy on average with a significant performance disparity across different political groups (50-95%). Augmenting the input context with expert-curated information can lead to a significant boost of approx. 9%, which remains an open challenge for automated RAG approaches, even considering curated content.
%R 10.18653/v1/2024.emnlp-main.312
%U https://aclanthology.org/2024.emnlp-main.312
%U https://doi.org/10.18653/v1/2024.emnlp-main.312
%P 5455-5467

Markdown (Informal)

[Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024](https://aclanthology.org/2024.emnlp-main.312) (Chalkidis, EMNLP 2024)

• Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024 (Chalkidis, EMNLP 2024)

ACL

• Ilias Chalkidis. 2024. Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5455–5467, Miami, Florida, USA. Association for Computational Linguistics.