chinese-text

用户反思其打字习惯，例如在中文文本中英文单词前后添加空格，正变得越来越像AI生成的文本。

This paper presents EVIL-Detect, a multi-signal ensemble framework with conflict-aware fusion for detecting LLM-generated, refined, and human-written Chinese text in the NLPCC 2026 Shared Task 6, achieving first place with a macro-F1 of 0.8888.

介绍7个GitHub项目，用于去除AI写作痕迹，涵盖中文和英文文本，包括qu-ai-wei、Humanizer等工具，帮助用户写出更像人写的文章。