<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-cho-2023-gta">
    <titleInfo>
        <title>GTA: Gated Toxicity Avoidance for LM Performance Preservation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Heegyu</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hyunsouk</namePart>
        <namePart type="family">Cho</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>Caution: This paper includes offensive words that could potentially cause unpleasantness. The fast-paced evolution of generative language models such as GPT-4 has demonstrated outstanding results in various NLP generation tasks. However, due to the potential generation of offensive words related to race or gender, various Controllable Text Generation (CTG) methods have been proposed to mitigate the occurrence of harmful words. However, existing CTG methods not only reduce toxicity but also negatively impact several aspects of the language model’s generation performance, including topic consistency, grammar, and perplexity. This paper explores the limitations of previous methods and introduces a novel solution in the form of a simple Gated Toxicity Avoidance (GTA) that can be applied to any CTG method. We also evaluate the effectiveness of the proposed GTA by comparing it with state-of-the-art CTG methods across various datasets. Our findings reveal that gated toxicity avoidance efficiently achieves comparable levels of toxicity reduction to the original CTG methods while preserving the generation performance of the language model.</abstract>
    <identifier type="citekey">kim-cho-2023-gta</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.983</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.983</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>14747</start>
            <end>14763</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GTA: Gated Toxicity Avoidance for LM Performance Preservation
%A Kim, Heegyu
%A Cho, Hyunsouk
%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 kim-cho-2023-gta
%X Caution: This paper includes offensive words that could potentially cause unpleasantness. The fast-paced evolution of generative language models such as GPT-4 has demonstrated outstanding results in various NLP generation tasks. However, due to the potential generation of offensive words related to race or gender, various Controllable Text Generation (CTG) methods have been proposed to mitigate the occurrence of harmful words. However, existing CTG methods not only reduce toxicity but also negatively impact several aspects of the language model’s generation performance, including topic consistency, grammar, and perplexity. This paper explores the limitations of previous methods and introduces a novel solution in the form of a simple Gated Toxicity Avoidance (GTA) that can be applied to any CTG method. We also evaluate the effectiveness of the proposed GTA by comparing it with state-of-the-art CTG methods across various datasets. Our findings reveal that gated toxicity avoidance efficiently achieves comparable levels of toxicity reduction to the original CTG methods while preserving the generation performance of the language model.
%R 10.18653/v1/2023.findings-emnlp.983
%U https://aclanthology.org/2023.findings-emnlp.983
%U https://doi.org/10.18653/v1/2023.findings-emnlp.983
%P 14747-14763

Markdown (Informal)

[GTA: Gated Toxicity Avoidance for LM Performance Preservation](https://aclanthology.org/2023.findings-emnlp.983) (Kim & Cho, Findings 2023)

• GTA: Gated Toxicity Avoidance for LM Performance Preservation (Kim & Cho, Findings 2023)

ACL

• Heegyu Kim and Hyunsouk Cho. 2023. GTA: Gated Toxicity Avoidance for LM Performance Preservation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14747–14763, Singapore. Association for Computational Linguistics.