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

Abstract

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

Categories

Framework mappings

Suggested from the entry's categories.

@misc{fasolino2026rag,
  title = {{In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning}},
  author = {Iliano Fasolino},
  year = {2026},
  month = sep,
  eprint = {2609.09243},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.09243}
}