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
Dataset
Year
2025
Publication link
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 |

