<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hira-etal-2026-language">
    <titleInfo>
        <title>The Language of Evidence: Robustness and Bias in Code-Switched RAG</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Medha</namePart>
        <namePart type="family">Hira</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joel</namePart>
        <namePart type="family">Mire</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maarten</namePart>
        <namePart type="family">Sap</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>Many people code-switch, mixing multiple languages within a single conversation, text or both in everyday communication and increasingly in interactions with AI systems. While prior work has examined how code-switching affects LLM outputs, its impact on RAG systems remains largely unexplored. We present a systematic study of multilingual retrieval under code-switched queries. First, we introduce a retrieval evaluation framework jointly measuring ranking accuracy, language alignment, and bilingual coverage, revealing language preferences that standard metrics obscure. In particular, the strongest relevance-performing retrievers tend to exhibit an English preference. Second, we propose Language-Targeted Contrastive Training to mitigate this retrieval bias, but find a fundamental trade-off: improving alignment reduces exposure to relevant content across languages. Third, controlled RAG experiments show that generation quality depends on retrieval language, with the preferred evidence language varying across query languages. Together, our findings expose tensions between retrieval accuracy, language coverage, and fairness in multilingual RAG, arguing for evaluation protocols that account for query-language coverage.</abstract>
    <identifier type="citekey">hira-etal-2026-language</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1830/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>41664</start>
            <end>41685</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Language of Evidence: Robustness and Bias in Code-Switched RAG
%A Hira, Medha
%A Mire, Joel
%A Sap, Maarten
%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 hira-etal-2026-language
%X Many people code-switch, mixing multiple languages within a single conversation, text or both in everyday communication and increasingly in interactions with AI systems. While prior work has examined how code-switching affects LLM outputs, its impact on RAG systems remains largely unexplored. We present a systematic study of multilingual retrieval under code-switched queries. First, we introduce a retrieval evaluation framework jointly measuring ranking accuracy, language alignment, and bilingual coverage, revealing language preferences that standard metrics obscure. In particular, the strongest relevance-performing retrievers tend to exhibit an English preference. Second, we propose Language-Targeted Contrastive Training to mitigate this retrieval bias, but find a fundamental trade-off: improving alignment reduces exposure to relevant content across languages. Third, controlled RAG experiments show that generation quality depends on retrieval language, with the preferred evidence language varying across query languages. Together, our findings expose tensions between retrieval accuracy, language coverage, and fairness in multilingual RAG, arguing for evaluation protocols that account for query-language coverage.
%U https://aclanthology.org/2026.emnlp-main.1830/
%P 41664-41685

Markdown (Informal)

[The Language of Evidence: Robustness and Bias in Code-Switched RAG](https://aclanthology.org/2026.emnlp-main.1830/) (Hira et al., EMNLP 2026)

• The Language of Evidence: Robustness and Bias in Code-Switched RAG (Hira et al., EMNLP 2026)

ACL

• Medha Hira, Joel Mire, and Maarten Sap. 2026. The Language of Evidence: Robustness and Bias in Code-Switched RAG. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 41664–41685, Budapest, Hungary. Association for Computational Linguistics.