SOURCE-LINKED INTELLIGENCE

In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if retrieved text is tampered with, the model may repeat the falsehood. We study how much a small quantized model, Llama 3.1 8B, degrades when a fraction of its retrieved context is poisoned. Three corruption strategies are tested, entity swap, number swap, and negation, each applied to zero, one, two, or three of the three retrieved passages, over a factorial sweep of 588 runs on a fact-checking task built from FEVER. Accuracy falls from 77.9% on

Read original source ↗ Open in workspace

recordType

paper

region

Global