<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-lee-2024-toward">
    <titleInfo>
        <title>Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seong-Il</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jay-Yoon</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024</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>Retrieval Augmented Language Models (RALMs) have gained significant attention for their ability to generate accurate answers and improve efficiency. However, RALMs are inherently vulnerable to imperfect information due to their reliance on the imperfect retriever or knowledge source. We identify three common scenarios—unanswerable, adversarial, conflicting—where retrieved document sets can confuse RALMs with plausible real-world examples. We present the first comprehensive investigation to assess how well RALMs detect and handle such problematic scenarios. Among these scenarios, to systematically examine adversarial robustness we propose a new adversarial attack method, Generative model-based ADVersarial attack (GenADV) and a novel metric Robustness under Additional Document (RAD). Our findings reveal that RALMs often fail to identify the unanswerability or contradiction of a document set, which frequently leads to hallucinations. Moreover, we show that the addition of an adversary significantly degrades RALM‘s performance, with the model becoming even more vulnerable when the two scenarios overlap (adversarial+ unanswerable). Our research identifies critical areas for assessing and enhancing the robustness of RALMs, laying the foundation for the development of more robust models.1</abstract>
    <identifier type="citekey">park-lee-2024-toward</identifier>
    <identifier type="doi">10.1162/tacl_a_00724</identifier>
    <location>
        <url>https://aclanthology.org/2024.tacl-1.91/</url>
    </location>
    <part>
        <date>2024</date>
        <detail type="volume"><number>12</number></detail>
        <extent unit="page">
            <start>1686</start>
            <end>1702</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models
%A Park, Seong-Il
%A Lee, Jay-Yoon
%J Transactions of the Association for Computational Linguistics
%D 2024
%V 12
%I MIT Press
%C Cambridge, MA
%F park-lee-2024-toward
%X Retrieval Augmented Language Models (RALMs) have gained significant attention for their ability to generate accurate answers and improve efficiency. However, RALMs are inherently vulnerable to imperfect information due to their reliance on the imperfect retriever or knowledge source. We identify three common scenarios—unanswerable, adversarial, conflicting—where retrieved document sets can confuse RALMs with plausible real-world examples. We present the first comprehensive investigation to assess how well RALMs detect and handle such problematic scenarios. Among these scenarios, to systematically examine adversarial robustness we propose a new adversarial attack method, Generative model-based ADVersarial attack (GenADV) and a novel metric Robustness under Additional Document (RAD). Our findings reveal that RALMs often fail to identify the unanswerability or contradiction of a document set, which frequently leads to hallucinations. Moreover, we show that the addition of an adversary significantly degrades RALM‘s performance, with the model becoming even more vulnerable when the two scenarios overlap (adversarial+ unanswerable). Our research identifies critical areas for assessing and enhancing the robustness of RALMs, laying the foundation for the development of more robust models.1
%R 10.1162/tacl_a_00724
%U https://aclanthology.org/2024.tacl-1.91/
%U https://doi.org/10.1162/tacl_a_00724
%P 1686-1702

Markdown (Informal)

[Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models](https://aclanthology.org/2024.tacl-1.91/) (Park & Lee, TACL 2024)

• Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models (Park & Lee, TACL 2024)

ACL

• Seong-Il Park and Jay-Yoon Lee. 2024. Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models. Transactions of the Association for Computational Linguistics, 12:1686–1702.