@inproceedings{park-rudzicz-2022-detoxifying,
title = "Detoxifying Language Models with a Toxic Corpus",
author = "Park, Yoona and
Rudzicz, Frank",
editor = "Chakravarthi, Bharathi Raja and
Bharathi, B and
McCrae, John P and
Zarrouk, Manel and
Bali, Kalika and
Buitelaar, Paul",
booktitle = "Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.ltedi-1.6",
doi = "10.18653/v1/2022.ltedi-1.6",
pages = "41--46",
abstract = "Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have been proposed, which are primarily categorized into data-based and decoding-based. In our study, we investigate the ensemble of the two debiasing paradigms, proposing to use toxic corpus as an additional resource to reduce the toxicity. Our result shows that toxic corpus can indeed help to reduce the toxicity of the language generation process substantially, complementing the existing debiasing methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-rudzicz-2022-detoxifying">
<titleInfo>
<title>Detoxifying Language Models with a Toxic Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoona</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Rudzicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Bharathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manel</namePart>
<namePart type="family">Zarrouk</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>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have been proposed, which are primarily categorized into data-based and decoding-based. In our study, we investigate the ensemble of the two debiasing paradigms, proposing to use toxic corpus as an additional resource to reduce the toxicity. Our result shows that toxic corpus can indeed help to reduce the toxicity of the language generation process substantially, complementing the existing debiasing methods.</abstract>
<identifier type="citekey">park-rudzicz-2022-detoxifying</identifier>
<identifier type="doi">10.18653/v1/2022.ltedi-1.6</identifier>
<location>
<url>https://aclanthology.org/2022.ltedi-1.6</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>41</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detoxifying Language Models with a Toxic Corpus
%A Park, Yoona
%A Rudzicz, Frank
%Y Chakravarthi, Bharathi Raja
%Y Bharathi, B.
%Y McCrae, John P.
%Y Zarrouk, Manel
%Y Bali, Kalika
%Y Buitelaar, Paul
%S Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F park-rudzicz-2022-detoxifying
%X Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have been proposed, which are primarily categorized into data-based and decoding-based. In our study, we investigate the ensemble of the two debiasing paradigms, proposing to use toxic corpus as an additional resource to reduce the toxicity. Our result shows that toxic corpus can indeed help to reduce the toxicity of the language generation process substantially, complementing the existing debiasing methods.
%R 10.18653/v1/2022.ltedi-1.6
%U https://aclanthology.org/2022.ltedi-1.6
%U https://doi.org/10.18653/v1/2022.ltedi-1.6
%P 41-46
Markdown (Informal)
[Detoxifying Language Models with a Toxic Corpus](https://aclanthology.org/2022.ltedi-1.6) (Park & Rudzicz, LTEDI 2022)
ACL
- Yoona Park and Frank Rudzicz. 2022. Detoxifying Language Models with a Toxic Corpus. In Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion, pages 41–46, Dublin, Ireland. Association for Computational Linguistics.