@inproceedings{de-ruvo-etal-2025-detoxify,
    title = "Detoxify-{IT}: An {I}talian Parallel Dataset for Text Detoxification",
    author = "De Ruvo, Viola  and
      Muti, Arianna  and
      Dementieva, Daryna  and
      Nozza, Debora",
    editor = "Calabrese, Agostina  and
      de Kock, Christine  and
      Nozza, Debora  and
      Plaza-del-Arco, Flor Miriam  and
      Talat, Zeerak  and
      Vargas, Francielle",
    booktitle = "Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.woah-1.24/",
    pages = "267--275",
    ISBN = "979-8-89176-105-6",
    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."
}