arXiv Machine Learning June 9, 2026 By Hyunseok Paeng

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

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 12

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

arXiv:2606. 13610v1 Announce Type: cross Abstract: Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content.

By Minghao Luo, Liang Chen

llms benchmarks

arXiv AI

Jun 17

Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems

arXiv:2606. 17443v1 Announce Type: new Abstract: Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new channel.

By Xi Chu, Yupeng Hou

llms robotics safety

arXiv AI

Jun 30

SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents

arXiv:2606. 28356v1 Announce Type: cross Abstract: Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems.

By Qianfeng Wen, Yifan Simon Liu, Xin Liu, Difan Jiao, Blair Yang, Junda Wu, Zhenwei Tang

llms agents

arXiv AI

Jun 30

Fairness Attacks on Recommender Systems

arXiv:2606. 29064v1 Announce Type: cross Abstract: The unfairness of recommender systems has become a topic of concern due to its significant social and ethical implications.

By Yanan Wang, Yong Ge

reinforcement-learning safety

arXiv AI

Aug 5

DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial

arXiv:2608. 02678v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems are vulnerable to corpus poisoning: an attacker who inserts a crafted document into the retrieval corpus can steer the underlying large language model (LLM) toward an attacker-chosen wrong answer.

By Abay Zhurekbay, Tao Liu, Fan Li

llms rag multimodal

Hugging Face Trending Papers

Jun 4

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.

llms reinforcement-learning safety

Related stories

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

Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems

SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents

Fairness Attacks on Recommender Systems

DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack