LLM Recommenders Vulnerable to Web Content Pollution
Minghao Luo · hf · 2026-08-25
A study evaluates web content pollution in LLM recommenders. It finds they are highly vulnerable to Generative Engine Optimization (GEO) pollution, frequently promoting fake products despite reasoning and defenses.
More from Safety
- Proposed probes to bring AI unconscious thoughts to human oversight — francoisfleuret · 2026-08-25
- Ex-Worker: AI Training Encouraged to Reward Hack Broken Environments — jd_pressman · 2026-08-25
- 2026 Singapore Consensus Sets Global AI Safety Research Priorities with 100+ Experts from 13 Countries — mikeflache · 2026-08-25
- Scotland Faces 1,600 Objections Against Planned 'World's Second Largest' Datacentre — nordicinst · 2026-08-25
- OpenAI urges California to strengthen AI safety bill — emmanuelvivier · 2026-08-25
- AI moderation fails to protect communities, humans needed — emmanuelvivier · 2026-08-25