Tag
A user reflects on how their typing habits, such as adding spaces around English words in Chinese text, are becoming more like AI-generated text.
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.
Introduces 7 GitHub projects for removing AI writing traces, covering both Chinese and English texts, including tools like qu-ai-wei and Humanizer, to help users write articles that sound more human.