Researchers have developed the Tatoxa system, a novel approach to text detoxification specifically for the Tatar language, which is considered low-resource. Experiments demonstrate that Tatoxa surpasses existing open-source and commercial large language models in detecting and mitigating harmful content. The study also introduced a new dataset for Tatar text detoxification and found that cross-lingual transfer from languages like Russian is less effective than training on native Tatar data. AI
IMPACT Enhances safety and accessibility of online content for low-resource languages like Tatar.
RANK_REASON The cluster describes a research paper detailing a new system for text detoxification in a low-resource language.
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
