The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar

  • 类型：arxiv
  • 标识：2606.26015
  • 链接：https://arxiv.org/abs/2606.26015
  • 主分类：risk
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：Tatoxa is presented, a novel state-of-the-art system for text detoxification in the Tatar language, and comparative experiments show that the proposed approach outperforms existing open source and proprietary commercial LLMs on key quality metrics.
  • OpenAlex ID：W7165960444
  • OpenAlex DOI：10.48550/arxiv.2606.26015
  • DOI：10.48550/arxiv.2606.26015
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2606.26015
  • OpenAlex更新：2026-07-19
  • 待LLM分类：否
  • 标题中文：The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar
  • TLDR中文：提出 Tatoxa，一种面向鞑靼语文本去毒的 SOTA 系统；对比实验表明，该方法在关键质量指标上优于现有开源及商用闭源 LLM。
  • 来源文件：
  • /inbox/tom/_candidates/2026-06-29-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]