<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dziri-etal-2022-evaluating">
    <titleInfo>
        <title>Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nouha</namePart>
        <namePart type="family">Dziri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hannah</namePart>
        <namePart type="family">Rashkin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tal</namePart>
        <namePart type="family">Linzen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Reitter</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022</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>Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires evaluation metrics that can quantify its prevalence. To this end, we introduce the Benchmark for Evaluation of Grounded INteraction (Begin), comprising 12k dialogue turns generated by neural dialogue systems trained on three knowledge-grounded dialogue corpora. We collect human annotations assessing the extent to which the models’ responses can be attributed to the given background information. We then use Begin to analyze eight evaluation metrics. We find that these metrics rely on spurious correlations, do not reliably distinguish attributable abstractive responses from unattributable ones, and perform substantially worse when the knowledge source is longer. Our findings underscore the need for more sophisticated and robust evaluation metrics for knowledge-grounded dialogue. We make Begin publicly available at https://github.com/google/BEGIN-dataset.</abstract>
    <identifier type="citekey">dziri-etal-2022-evaluating</identifier>
    <identifier type="doi">10.1162/tacl_a_00506</identifier>
    <location>
        <url>https://aclanthology.org/2022.tacl-1.62/</url>
    </location>
    <part>
        <date>2022</date>
        <detail type="volume"><number>10</number></detail>
        <extent unit="page">
            <start>1066</start>
            <end>1083</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark
%A Dziri, Nouha
%A Rashkin, Hannah
%A Linzen, Tal
%A Reitter, David
%J Transactions of the Association for Computational Linguistics
%D 2022
%V 10
%I MIT Press
%C Cambridge, MA
%F dziri-etal-2022-evaluating
%X Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires evaluation metrics that can quantify its prevalence. To this end, we introduce the Benchmark for Evaluation of Grounded INteraction (Begin), comprising 12k dialogue turns generated by neural dialogue systems trained on three knowledge-grounded dialogue corpora. We collect human annotations assessing the extent to which the models’ responses can be attributed to the given background information. We then use Begin to analyze eight evaluation metrics. We find that these metrics rely on spurious correlations, do not reliably distinguish attributable abstractive responses from unattributable ones, and perform substantially worse when the knowledge source is longer. Our findings underscore the need for more sophisticated and robust evaluation metrics for knowledge-grounded dialogue. We make Begin publicly available at https://github.com/google/BEGIN-dataset.
%R 10.1162/tacl_a_00506
%U https://aclanthology.org/2022.tacl-1.62/
%U https://doi.org/10.1162/tacl_a_00506
%P 1066-1083

Markdown (Informal)

[Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark](https://aclanthology.org/2022.tacl-1.62/) (Dziri et al., TACL 2022)

• Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark (Dziri et al., TACL 2022)

ACL

• Nouha Dziri, Hannah Rashkin, Tal Linzen, and David Reitter. 2022. Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark. Transactions of the Association for Computational Linguistics, 10:1066–1083.