DeGenTWeb 论文测量 MGT 主导网站占比
DeGenTWeb: A First Look at MGT-dominant Websites
AI 导读
研究者提出 DeGenTWeb 框架，系统识别信息性内容以大语言模型生成文本为主的网站，并公开将把代码与数据发布。论文将 MGT 检测器适配到网页级并聚合多页面结果做站点级判定，误判人类撰写网站为 MGT 主导的比例仅 0.12%。
推荐理由
论文给出可复用的站点级 MGT 检测框架和代表性测量结果，填补了此前新闻式估计方法不透明的背景。
正文 · 原文
Abstract:Many news reports have claimed that machine-generated text (MGT) from large language models (LLMs) is taking over the web. However, these claims are typically not based on a representative sample of the web, and the methodology underlying them is often opaque. Consequently, we lack an understanding of the true prevalence and characteristics of MGT on the web.
We describe DeGenTWeb, which systematically identifies MGT-dominant websites: sites whose informational prose content is mostly MGT, with little human input. We show how to adapt detectors of MGT for use on web pages, and how to aggregate detection results from multiple pages on a site for accurate site-level categorization. DeGenTWeb mislabels only 0.12% of human-authored sites as MGT-dominant. We find that 20.9% of the sites archived by Common Crawl between January and July 2026 and 13.6% of the sites linked from Bing's search results in 2025 are MGT-dominant. These figures are lower bounds on the prevalence of MGT-dominant sites. We also find that the fraction of MGT-dominant sites is growing over time, and that many such sites share the same owner. We will release all of our code and data after publication.
| Comments: | In submission; 13 pages, 8 figures |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Information Retrieval (cs.IR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.00087 [cs.NI] |
| (or arXiv:2605.00087v2 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.00087 arXiv-issued DOI via DataCite |
Submission history
From: Sichang He [view email]
[v1]
Thu, 30 Apr 2026 17:54:35 UTC (994 KB)
[v2]
Mon, 26 Oct 2026 18:38:07 UTC (1,915 KB)
来源：arXiv cs.AI · arxiv.org