One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders

• 类型：arxiv
• 标识：2606.13610
• 链接：https://arxiv.org/abs/2606.13610
• 主分类：rag
• 形态：method
• TLDR：Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: LLM recommenders may consume web content that Generative Engine Optimization (GEO) operators have polluted to mislead them. We ask: to what extent do they become unwitting promoters of fake products? We introduce FORGE (Fake Online Recommendations in Generative Environments), which locally rewrites real products in a frozen set of retrieved web pages into fake ones and measures how often the LLM recommends the fake product, across 225 real products in 15 categor
• 副分类：evaluation
• 待LLM分类：否
• 标题中文：一页污染足矣：评测 LLM 推荐系统中的网页内容污染
• TLDR中文：检索增强 LLM 越来越多地通过抓取实时网页内容来影响日常消费推荐。这带来一种新风险：LLM 推荐系统可能会摄入被生成式引擎优化（GEO）运营者污染、用于误导其判断的网页内容。我们追问：它们在多大程度上会成为假产品的无意推广者？我们提出 FORGE（Fake Online Recommendations in Generative Environments），在本地将一组固定已抓取网页中的真实商品改写为假商品，并衡量 LLM 跨 15 个类目中 225 件真实商品推荐假商品的频率。
• 来源文件：
• /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json