Retrieval Collapses When AI Pollutes the Web

The rapid proliferation of AI-generated content on the Web presents a structural risk to information retrieval, as search engines and Retrieval-Augmented Generation (RAG) systems increasingly consume evidence produced by the Large Language Models (LLMs). We characterize this ecosystem-level failure mode as Retrieval Collapse, a two-stage process where (1) AI-generated content dominates search results, eroding source diversity, and (2) low-quality or adversarial content infiltrates the retrieval pipeline. We analyzed this dynamic through controlled experiments involving both high-quality SEO-style content and adversarially crafted content. In the SEO scenario, a 67\% pool contamination led to over 80\% exposure contamination, creating a homogenized yet deceptively healthy state where answer accuracy remains stable despite the reliance on synthetic sources. Conversely, under adversarial contamination, baselines like BM25 exposed $\sim$19\% of harmful content, whereas LLM-based rankers demonstrated stronger suppression capabilities. These findings highlight the risk of retrieval pipelines quietly shifting toward synthetic evidence and the need for retrieval-aware strategies to prevent a self-reinforcing cycle of quality decline in Web-grounded systems.

Key Contributions

• Formalizes 'Retrieval Collapse' as a two-stage ecosystem failure mode (dominance/homogenization followed by adversarial pollution) distinct from training-time model collapse
• Empirically quantifies contamination dynamics: 67% pool contamination yields >80% exposure contamination in SEO settings and ~19% harmful content exposure in BM25 under adversarial conditions
• Shows LLM-based rankers suppress adversarial content more effectively than BM25, while both are vulnerable to SEO-style homogenization

🛡️ Threat Analysis

Details

Similar Papers