Sichang Steven He

Sichang Steven He, Calvin Ardi, Ramesh Govindan et al.

Many recent news reports have claimed that content generated by 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. Moreover, when aiming to minimize the chances of falsely attributing human-authored content to LLMs, we find that detectors of LLM-generated text perform much worse than advertised. Consequently, we lack an understanding of the true prevalence and characteristics of LLM content on the web. We describe DeGenTWeb which systematically identifies LLM-dominant websites: sites whose content has been generated using LLMs with little human input. We show how to adapt detectors of LLM-generated text for use on web pages, and how to aggregate detection results from multiple pages on a site for accurate site-level categorization. Using DeGenTWeb, we find that LLM-dominant sites are highly prevalent both in data from Common Crawl and in Bing's search results, and that this share is growing over time. We also show that continuing to accurately identify such sites appears challenging given the capabilities of the latest LLMs.

Sichang Steven He, Ramesh Govindan, Harsha V. Madhyastha

Increasingly, web content is automatically generated by large language models (LLMs) with little human input. We call this "LLM-dominant" content. Since LLMs plagiarize and hallucinate, LLM-dominant content can be unreliable and unethical. Yet, websites rarely disclose such content, and human readers struggle to distinguish it. Thus, we must develop reliable detectors for LLM-dominant content. However, state-of-the-art LLM detectors are inaccurate on web content, because web content has low positive rates, complex markup, and diverse genres, instead of clean, prose-like benchmark data SoTA detectors are optimized for. We propose a highly reliable, scalable pipeline that classifies entire websites. Instead of naively classifying text extracted from each page, we classify each site based on an LLM text detector's outputs of multiple prose-like pages to boost accuracies. We train and evaluate our detector by collecting 2 distinct ground truth datasets totaling 120 sites, and obtain 100% accuracies testing across them. In the wild, we detect a sizable portion of sites as LLM-dominant among 10k sites in search engine results and 10k in Common Crawl archives. We find LLM-dominant sites are growing in prevalence and rank highly in search results, raising questions about their impact on end users and the overall Web ecosystem.