<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bergman-etal-2022-guiding">
    <titleInfo>
        <title>Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">A</namePart>
        <namePart type="given">Stevie</namePart>
        <namePart type="family">Bergman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gavin</namePart>
        <namePart type="family">Abercrombie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shannon</namePart>
        <namePart type="family">Spruit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dirk</namePart>
        <namePart type="family">Hovy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emily</namePart>
        <namePart type="family">Dinan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Y-Lan</namePart>
        <namePart type="family">Boureau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Verena</namePart>
        <namePart type="family">Rieser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Edinburgh, UK</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Over the last several years, end-to-end neural conversational agents have vastly improved their ability to carry unrestricted, open-domain conversations with humans. However, these models are often trained on large datasets from the Internet and, as a result, may learn undesirable behaviours from this data, such as toxic or otherwise harmful language. Thus, researchers must wrestle with how and when to release these models. In this paper, we survey recent and related work to highlight tensions between values, potential positive impact, and potential harms. We also provide a framework to support practitioners in deciding whether and how to release these models, following the tenets of value-sensitive design.</abstract>
    <identifier type="citekey">bergman-etal-2022-guiding</identifier>
    <location>
        <url>https://aclanthology.org/2022.sigdial-1.4</url>
    </location>
    <part>
        <date>2022-09</date>
        <extent unit="page">
            <start>39</start>
            <end>52</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design
%A Bergman, A. Stevie
%A Abercrombie, Gavin
%A Spruit, Shannon
%A Hovy, Dirk
%A Dinan, Emily
%A Boureau, Y-Lan
%A Rieser, Verena
%S Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2022
%8 September
%I Association for Computational Linguistics
%C Edinburgh, UK
%F bergman-etal-2022-guiding
%X Over the last several years, end-to-end neural conversational agents have vastly improved their ability to carry unrestricted, open-domain conversations with humans. However, these models are often trained on large datasets from the Internet and, as a result, may learn undesirable behaviours from this data, such as toxic or otherwise harmful language. Thus, researchers must wrestle with how and when to release these models. In this paper, we survey recent and related work to highlight tensions between values, potential positive impact, and potential harms. We also provide a framework to support practitioners in deciding whether and how to release these models, following the tenets of value-sensitive design.
%U https://aclanthology.org/2022.sigdial-1.4
%P 39-52

Markdown (Informal)

[Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design](https://aclanthology.org/2022.sigdial-1.4) (Bergman et al., SIGDIAL 2022)

• Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design (Bergman et al., SIGDIAL 2022)

ACL

• A. Stevie Bergman, Gavin Abercrombie, Shannon Spruit, Dirk Hovy, Emily Dinan, Y-Lan Boureau, and Verena Rieser. 2022. Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 39–52, Edinburgh, UK. Association for Computational Linguistics.