← Back to all news
arXiv AI By Minghao Luo, Liang Chen

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

Read the original on arXiv AI →

The paper introduces FORGE, a benchmark that rewrites real product pages into fake ones to test how often search‑augmented large language models (LLMs) recommend these polluted items. Across 12 commercial and open‑weight LLMs, a single polluted page can lead to up to 27% of recommendations being fake, rising to 73.8% when the top‑3 replacements are used. The study finds that reasoning does not help and existing defenses—skepticism prompts, consensus filters, and credibility re‑ranking—are largely ineffective.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 10

Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning

arXiv:2609.06027v1 Announce Type: cross Abstract: Search-augmented LLM agents are increasingly used for consumer decisions, making them vulnerable to Generative Engine Optimization (GEO) poisoning. E...

By Zhongan Bi, Qiwen Wang, Jianrong Jiang, Jigang Ding, Wenwen Xiong, Changhua Meng, Xuanang Gao, Kepeng Lin, Changjiang Jiang, Yiang Chen, Huan Yao, Wei Wang, Zhenyu Ma, Wenhui Dong
llmsagentsbenchmarks
More like this →
arXiv Machine Learning
Jun 9

The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection

arXiv:2606. 09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedded in retrieved documents backfire against the attacker, suppressing the target brand below the injection-free baseline.

By Hyunseok Paeng
llmsragsafety
More like this →
arXiv AI
Sep 4

When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization

The paper introduces GEO Defender, a two‑stage defense system designed to protect generative search engines from malicious Generative Engine Optimization (GEO) attacks that rewrite web documents to manipulate generated answers. GEO Defender comprises a Shield Reranker, which learns a defensive residual to demote GEO‑rewritten documents while maintaining relevance, and a Training‑Free Shield Generation component that creates a natural‑language library guiding the target LLM’s source usage during inference. Experiments on both closed‑source and open‑source large language models show that GEO Defender dramatically lowers attack success rates from 50.32% to 6.20%, preserves over 94% of benign evidence usage, and maintains answer quality while generalizing to unseen attacks.

By Haozhang Li, Yangguang Shao, Xinjie Lin, Zhong Guan, Mi Zhou, Junzheng Shi
llmsagentsroboticsfine-tuningbenchmarks
More like this →