<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-sagae-2021-automatically">
    <titleInfo>
        <title>Automatically Exposing Problems with Neural Dialog Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dian</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kenji</namePart>
        <namePart type="family">Sagae</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural dialog models are known to suffer from problems such as generating unsafe and inconsistent responses. Even though these problems are crucial and prevalent, they are mostly manually identified by model designers through interactions. Recently, some research instructs crowdworkers to goad the bots into triggering such problems. However, humans leverage superficial clues such as hate speech, while leaving systematic problems undercover. In this paper, we propose two methods including reinforcement learning to automatically trigger a dialog model into generating problematic responses. We show the effect of our methods in exposing safety and contradiction issues with state-of-the-art dialog models.</abstract>
    <identifier type="citekey">yu-sagae-2021-automatically</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.37</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.37</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>456</start>
            <end>470</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Automatically Exposing Problems with Neural Dialog Models
%A Yu, Dian
%A Sagae, Kenji
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F yu-sagae-2021-automatically
%X Neural dialog models are known to suffer from problems such as generating unsafe and inconsistent responses. Even though these problems are crucial and prevalent, they are mostly manually identified by model designers through interactions. Recently, some research instructs crowdworkers to goad the bots into triggering such problems. However, humans leverage superficial clues such as hate speech, while leaving systematic problems undercover. In this paper, we propose two methods including reinforcement learning to automatically trigger a dialog model into generating problematic responses. We show the effect of our methods in exposing safety and contradiction issues with state-of-the-art dialog models.
%R 10.18653/v1/2021.emnlp-main.37
%U https://aclanthology.org/2021.emnlp-main.37
%U https://doi.org/10.18653/v1/2021.emnlp-main.37
%P 456-470

Markdown (Informal)

[Automatically Exposing Problems with Neural Dialog Models](https://aclanthology.org/2021.emnlp-main.37) (Yu & Sagae, EMNLP 2021)

• Automatically Exposing Problems with Neural Dialog Models (Yu & Sagae, EMNLP 2021)

ACL

• Dian Yu and Kenji Sagae. 2021. Automatically Exposing Problems with Neural Dialog Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 456–470, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.