<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2023-personalized">
    <titleInfo>
        <title>Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yixin</namePart>
        <namePart type="family">Wan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jieyu</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aman</namePart>
        <namePart type="family">Chadha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nanyun</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kai-Wei</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as “an Asian person”, whereas specific personas may take the form of specific popular Asian names like “Yumi”. While the adoption of personas enriches user experiences by making dialogue systems more engaging and approachable, it also casts a shadow of potential risk by exacerbating social biases within model responses, thereby causing societal harm through interactions with users. In this paper, we systematically study “persona biases”, which we define to be the sensitivity of dialogue models’ harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement. Additionally, we propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a systematically constructed persona dataset encompassing various types of both generic and specific model personas. Through benchmarking on four different models- including Blender, ChatGPT, Alpaca, and Vicuna- our study uncovers significant persona biases in dialogue systems. Our findings also underscore the pressing need to revisit the use of personas in dialogue agents to ensure safe application.</abstract>
    <identifier type="citekey">wan-etal-2023-personalized</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.648</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.648</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>9677</start>
            <end>9705</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems
%A Wan, Yixin
%A Zhao, Jieyu
%A Chadha, Aman
%A Peng, Nanyun
%A Chang, Kai-Wei
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wan-etal-2023-personalized
%X Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as “an Asian person”, whereas specific personas may take the form of specific popular Asian names like “Yumi”. While the adoption of personas enriches user experiences by making dialogue systems more engaging and approachable, it also casts a shadow of potential risk by exacerbating social biases within model responses, thereby causing societal harm through interactions with users. In this paper, we systematically study “persona biases”, which we define to be the sensitivity of dialogue models’ harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement. Additionally, we propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a systematically constructed persona dataset encompassing various types of both generic and specific model personas. Through benchmarking on four different models- including Blender, ChatGPT, Alpaca, and Vicuna- our study uncovers significant persona biases in dialogue systems. Our findings also underscore the pressing need to revisit the use of personas in dialogue agents to ensure safe application.
%R 10.18653/v1/2023.findings-emnlp.648
%U https://aclanthology.org/2023.findings-emnlp.648
%U https://doi.org/10.18653/v1/2023.findings-emnlp.648
%P 9677-9705

Markdown (Informal)

[Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://aclanthology.org/2023.findings-emnlp.648) (Wan et al., Findings 2023)

• Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems (Wan et al., Findings 2023)

ACL

• Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, and Kai-Wei Chang. 2023. Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9677–9705, Singapore. Association for Computational Linguistics.