<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2023-controlled">
    <titleInfo>
        <title>Controlled Text Generation with Hidden Representation Transformations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vaibhav</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hana</namePart>
        <namePart type="family">Koorehdavoudi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masud</namePart>
        <namePart type="family">Moshtaghi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amita</namePart>
        <namePart type="family">Misra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ankit</namePart>
        <namePart type="family">Chadha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emilio</namePart>
        <namePart type="family">Ferrara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose CHRT (Control HiddenRepresentation Transformation) – a con-trolled language generation framework thatsteers large language models to generatetext pertaining to certain attributes (such astoxicity). CHRT gains attribute control bymodifying the hidden representation of thebase model through learned transformations. We employ a contrastive-learning frameworkto learn these transformations that can becombined to gain multi-attribute control. Theeffectiveness of CHRT is experimentallyshown by comparing it with seven baselinesover three attributes. CHRT outperforms all thebaselines in the task of detoxification, positivesentiment steering, and text simplificationwhile minimizing the loss in linguistic qualities. Further, our approach has the lowest inferencelatency of only 0.01 seconds more than thebase model, making it the most suitable forhigh-performance production environments. We open-source our code and release two noveldatasets to further propel controlled languagegeneration research</abstract>
    <identifier type="citekey">kumar-etal-2023-controlled</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.602</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.602</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>9440</start>
            <end>9455</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Controlled Text Generation with Hidden Representation Transformations
%A Kumar, Vaibhav
%A Koorehdavoudi, Hana
%A Moshtaghi, Masud
%A Misra, Amita
%A Chadha, Ankit
%A Ferrara, Emilio
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kumar-etal-2023-controlled
%X We propose CHRT (Control HiddenRepresentation Transformation) – a con-trolled language generation framework thatsteers large language models to generatetext pertaining to certain attributes (such astoxicity). CHRT gains attribute control bymodifying the hidden representation of thebase model through learned transformations. We employ a contrastive-learning frameworkto learn these transformations that can becombined to gain multi-attribute control. Theeffectiveness of CHRT is experimentallyshown by comparing it with seven baselinesover three attributes. CHRT outperforms all thebaselines in the task of detoxification, positivesentiment steering, and text simplificationwhile minimizing the loss in linguistic qualities. Further, our approach has the lowest inferencelatency of only 0.01 seconds more than thebase model, making it the most suitable forhigh-performance production environments. We open-source our code and release two noveldatasets to further propel controlled languagegeneration research
%R 10.18653/v1/2023.findings-acl.602
%U https://aclanthology.org/2023.findings-acl.602
%U https://doi.org/10.18653/v1/2023.findings-acl.602
%P 9440-9455

Markdown (Informal)

[Controlled Text Generation with Hidden Representation Transformations](https://aclanthology.org/2023.findings-acl.602) (Kumar et al., Findings 2023)

• Controlled Text Generation with Hidden Representation Transformations (Kumar et al., Findings 2023)

ACL

• Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi, Amita Misra, Ankit Chadha, and Emilio Ferrara. 2023. Controlled Text Generation with Hidden Representation Transformations. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9440–9455, Toronto, Canada. Association for Computational Linguistics.