@inproceedings{el-attar-etal-2026-leveraging,
title = "Leveraging Comparable Toxicity Lexicons in Prompt Instructions for Multilingual Text Detoxification",
author = {El Attar, Yassir and
D{\"o}nmez, Esra and
Ohlendorf, Nina K. and
Falenska, Agnieszka},
editor = "Rapp, Reinhard and
Terryn, Ayla Rigouts and
Sharoff, Serge and
Zweigenbaum, Pierre",
booktitle = "Proceedings of the 19th Workshop on Building and Using Comparable Corpora ({BUCC})",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.bucc-1.12/",
doi = "10.63317/2f5i2922qqe2",
pages = "108--118",
abstract = "To mitigate the prevalence of toxic language on digital social media, various NLP approaches have been proposed for automatic text detoxification. However, the potential of toxic expression lexicons as a comparable cross-lingual resource to guide this process remains largely unexplored. In this work, we investigate how such resources can be effectively used to inform multilingual language models about what should and should not be considered toxic. We evaluate four models under two settings{---}zero-shot prompting and fine-tuning{---}to assess the impact of incorporating toxic expressions in prompt instruction, including in cross-lingual transfer scenarios. Our results show that both zero-shot prompting and fine-tuning approaches benefit considerably from adding toxic expressions in prompt instructions during training and/or inference. Our findings demonstrate that comparable, lightweight, language-specific toxic expression lexicons constitute an effective mechanism for injecting explicit information about lexical toxicity into multilingual language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-attar-etal-2026-leveraging">
<titleInfo>
<title>Leveraging Comparable Toxicity Lexicons in Prompt Instructions for Multilingual Text Detoxification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yassir</namePart>
<namePart type="family">El Attar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esra</namePart>
<namePart type="family">Dönmez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Ohlendorf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Falenska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="given">Rigouts</namePart>
<namePart type="family">Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To mitigate the prevalence of toxic language on digital social media, various NLP approaches have been proposed for automatic text detoxification. However, the potential of toxic expression lexicons as a comparable cross-lingual resource to guide this process remains largely unexplored. In this work, we investigate how such resources can be effectively used to inform multilingual language models about what should and should not be considered toxic. We evaluate four models under two settings—zero-shot prompting and fine-tuning—to assess the impact of incorporating toxic expressions in prompt instruction, including in cross-lingual transfer scenarios. Our results show that both zero-shot prompting and fine-tuning approaches benefit considerably from adding toxic expressions in prompt instructions during training and/or inference. Our findings demonstrate that comparable, lightweight, language-specific toxic expression lexicons constitute an effective mechanism for injecting explicit information about lexical toxicity into multilingual language models.</abstract>
<identifier type="citekey">el-attar-etal-2026-leveraging</identifier>
<identifier type="doi">10.63317/2f5i2922qqe2</identifier>
<location>
<url>https://aclanthology.org/2026.bucc-1.12/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>108</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Comparable Toxicity Lexicons in Prompt Instructions for Multilingual Text Detoxification
%A El Attar, Yassir
%A Dönmez, Esra
%A Ohlendorf, Nina K.
%A Falenska, Agnieszka
%Y Rapp, Reinhard
%Y Terryn, Ayla Rigouts
%Y Sharoff, Serge
%Y Zweigenbaum, Pierre
%S Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F el-attar-etal-2026-leveraging
%X To mitigate the prevalence of toxic language on digital social media, various NLP approaches have been proposed for automatic text detoxification. However, the potential of toxic expression lexicons as a comparable cross-lingual resource to guide this process remains largely unexplored. In this work, we investigate how such resources can be effectively used to inform multilingual language models about what should and should not be considered toxic. We evaluate four models under two settings—zero-shot prompting and fine-tuning—to assess the impact of incorporating toxic expressions in prompt instruction, including in cross-lingual transfer scenarios. Our results show that both zero-shot prompting and fine-tuning approaches benefit considerably from adding toxic expressions in prompt instructions during training and/or inference. Our findings demonstrate that comparable, lightweight, language-specific toxic expression lexicons constitute an effective mechanism for injecting explicit information about lexical toxicity into multilingual language models.
%R 10.63317/2f5i2922qqe2
%U https://aclanthology.org/2026.bucc-1.12/
%U https://doi.org/10.63317/2f5i2922qqe2
%P 108-118
Markdown (Informal)
[Leveraging Comparable Toxicity Lexicons in Prompt Instructions for Multilingual Text Detoxification](https://aclanthology.org/2026.bucc-1.12/) (El Attar et al., BUCC 2026)
ACL