Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models
This addresses the problem of adapting detoxification methods across languages for users in multilingual contexts, but it is incremental as it highlights limitations rather than breakthroughs.
The study tackled multilingual and cross-lingual detoxification, finding that large multilingual models can perform multilingual style transfer but fail at cross-lingual detoxification without direct fine-tuning in the target language.
Detoxification is a task of generating text in polite style while preserving meaning and fluency of the original toxic text. Existing detoxification methods are designed to work in one exact language. This work investigates multilingual and cross-lingual detoxification and the behavior of large multilingual models like in this setting. Unlike previous works we aim to make large language models able to perform detoxification without direct fine-tuning in given language. Experiments show that multilingual models are capable of performing multilingual style transfer. However, models are not able to perform cross-lingual detoxification and direct fine-tuning on exact language is inevitable.