Papers › SmurfCat at PAN 2024 TextDetox: Alignment of Multilingual Transformers for Text Detoxification

SmurfCat at PAN 2024 TextDetox: Alignment of Multilingual Transformers for Text Detoxification

7 Jul 2024arXiv:2407.05449archive 2025-07-28

Elisei Rykov, Konstantin Zaytsev, Ivan Anisimov, Alexandr Voronin

This paper presents a solution for the Multilingual Text Detoxification task in the PAN-2024 competition of the SmurfCat team. Using data augmentation through machine translation and a special filtering procedure, we collected an additional multilingual parallel dataset for text detoxification. Using the obtained data, we fine-tuned several multilingual sequence-to-sequence models, such as mT0 and Aya, on a text detoxification task. We applied the ORPO alignment technique to the final model. Our final model has only 3.7 billion parameters and achieves state-of-the-art results for the Ukrainian language and near state-of-the-art results for other languages. In the competition, our team achieved first place in the automated evaluation with a score of 0.52 and second place in the final human evaluation with a score of 0.74.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

s-nlp/multilingual-transformer-detoxification officialmentioned in paperpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationMachine Translation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

mT0

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections