Multilingual Text Detoxification

Identification of toxicity in user texts is an active area of research, given that social networks are trying to address the problem of toxicity. Given a toxic piece of text, the task consists on re-writing it in a non-toxic way while saving the main content as much as possible.

Publication
Dementieva et al (2025) Overview of the Multilingual Text Detoxification Task at PAN 2025. In Proceedings of CLEF 2025, CEUR Workshop Proceedings.
Language
Spanish
French
Hindi
Italian
Ukrainian
NLP topic
Year
2025
Ranking metric
Joint

Task results

System joint Sort ascending
Team MetaDetox 0.7190
Jiaozipi 0.7120
adugeen 0.7090
SVATS 0.6980
sky.Duan 0.6960
Team Pratham 0.6960
jellyproll 0.6960

If you have published a result better than those on the list, send a message to odesia-comunicacion@lsi.uned.es indicating the result and the DOI of the article, along with a copy of it if it is not published openly.