一个被污染的页面就够了:评估生成式推荐系统中的网页内容污染
One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders
AI总结:
本研究提出FORGE基准,评估搜索增强LLM在检索结果被污染时推荐虚假产品的脆弱性,发现单个污染页面即可导致高达27%的推荐错误率,且推理能力无法缓解此问题。
摘要:
搜索增强的大语言模型通过检索实时网页内容越来越多地介入日常消费者推荐。这带来了新的风险:生成式推荐系统可能消费被污染的网页内容,例如旨在误导推荐的虚假评论和推广页面。我们提出:在消费被污染的检索结果时,搜索增强的LLM在多大程度上会成为虚假产品的无意推广者?为此,我们引入FORGE(生成环境中的虚假在线推荐),这是一个在受控网页内容污染下衡量虚假产品推荐的基准。给定上游搜索结果,FORGE将检索到的网页中的真实产品本地重写为虚假产品,以模拟网页内容污染,并测量LLM推荐虚假产品的频率。FORGE涵盖15个类别和5个消费者场景下的225个真实世界产品。在12个商业和开源LLM中,所有模型都易受影响:单个被污染的页面即可导致高达27%的被欺骗率,而完全替换前三个结果则将此比例提升至73.8%。不同类别间的脆弱性差异显著,当模型缺乏相关产品的稳定先验知识时,脆弱性增加。推理并不能缓解这种脆弱性;相反,它常常生成虚假的社会证明来为错误推荐辩护。我们评估了三种防御措施:怀疑提示和共识过滤(基于模型先验或跨文档证据)。怀疑可能加剧脆弱性,类似于推理,而过滤则可能抑制合法产品。我们在以下网址发布FORGE:this https URL。
英文摘要:
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 categories and 5 consumer scenarios. Across 12 commercial and open-weights LLMs, all models are vulnerable: a single polluted page yields fooled rates of up to 27%, while the full top-3 replacement raises this to 73.8%. Vulnerability varies across categories, increasing when models lack stable prior knowledge of the products. Reasoning does not mitigate this vulnerability; instead, it often generates spurious social proof to justify false recommendations. None of the four defenses is adequate: the skepticism prompt can exacerbate vulnerability much like reasoning, the two consensus filters risk suppressing legitimate products, and credibility re-ranking helps every model but removes only a sixth of the fakes. We release the FORGE benchmark and the evaluation code at https://github.com/leoluolol/forge-benchmark.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。