<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-ruvo-etal-2025-detoxify">
    <titleInfo>
        <title>Detoxify-IT: An Italian Parallel Dataset for Text Detoxification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Viola</namePart>
        <namePart type="family">De Ruvo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arianna</namePart>
        <namePart type="family">Muti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daryna</namePart>
        <namePart type="family">Dementieva</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Debora</namePart>
        <namePart type="family">Nozza</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Agostina</namePart>
            <namePart type="family">Calabrese</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christine</namePart>
            <namePart type="family">de Kock</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debora</namePart>
            <namePart type="family">Nozza</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Flor</namePart>
            <namePart type="given">Miriam</namePart>
            <namePart type="family">Plaza-del-Arco</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zeerak</namePart>
            <namePart type="family">Talat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Francielle</namePart>
            <namePart type="family">Vargas</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-105-6</identifier>
    </relatedItem>
    <abstract>Toxic language online poses growing challenges for content moderation. Detoxification, which rewrites toxic content into neutral form, offers a promising alternative but remains underexplored beyond English. We present Detoxify-IT, the first Italian dataset for this task, featuring toxic comments and their human-written neutral rewrites. Our experiments show that even limited fine-tuning on Italian data leads to notable improvements in content preservation and fluency compared to both multilingual models and LLMs used in zero-shot settings, underlining the need for language-specific resources. This work enables detoxification research in Italian and supports broader efforts toward safer, more inclusive online communication.</abstract>
    <identifier type="citekey">de-ruvo-etal-2025-detoxify</identifier>
    <location>
        <url>https://aclanthology.org/2025.woah-1.24/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>267</start>
            <end>275</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Detoxify-IT: An Italian Parallel Dataset for Text Detoxification
%A De Ruvo, Viola
%A Muti, Arianna
%A Dementieva, Daryna
%A Nozza, Debora
%Y Calabrese, Agostina
%Y de Kock, Christine
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Talat, Zeerak
%Y Vargas, Francielle
%S Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-105-6
%F de-ruvo-etal-2025-detoxify
%X Toxic language online poses growing challenges for content moderation. Detoxification, which rewrites toxic content into neutral form, offers a promising alternative but remains underexplored beyond English. We present Detoxify-IT, the first Italian dataset for this task, featuring toxic comments and their human-written neutral rewrites. Our experiments show that even limited fine-tuning on Italian data leads to notable improvements in content preservation and fluency compared to both multilingual models and LLMs used in zero-shot settings, underlining the need for language-specific resources. This work enables detoxification research in Italian and supports broader efforts toward safer, more inclusive online communication.
%U https://aclanthology.org/2025.woah-1.24/
%P 267-275

Markdown (Informal)

[Detoxify-IT: An Italian Parallel Dataset for Text Detoxification](https://aclanthology.org/2025.woah-1.24/) (De Ruvo et al., WOAH 2025)

• Detoxify-IT: An Italian Parallel Dataset for Text Detoxification (De Ruvo et al., WOAH 2025)

ACL

• Viola De Ruvo, Arianna Muti, Daryna Dementieva, and Debora Nozza. 2025. Detoxify-IT: An Italian Parallel Dataset for Text Detoxification. In Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH), pages 267–275, Vienna, Austria. Association for Computational Linguistics.