多语言机器生成文本的作者归属研究，ACL 2026 主会论文，为检测 AI 文本提供新思路。
arXiv:2508.01656v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishin…
零样本快速检测AI生成文本新方法，基于困惑度与文本洗牌，无需训练数据即可高效识别。
arXiv:2604.25860v2 Announce Type: replace-cross Abstract: Machine-generated text (MGT) detection requires identifying structurally invariant signals a…
针对Wikipedia真实编辑场景的LLM文本检测新基准TSM-Bench发布，填补了现有泛化基准的空白。
arXiv:2605.31113v1 Announce Type: new Abstract: Automatically detecting machine-generated text (MGT) is critical to maintaining the knowledge integrit…