mlsanityData to 14 Oct 2026

Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval

arXiv 2606.07783 ↗First posted 5 Jun 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) is widely used to improve the factual reliability of large language models (LLMs) by grounding answers in retrieved evidence. In misinformation-rich environments, however, retrieved content may include plausible but incorrect information, raising concerns about the reliability of RAG-based information access systems. In this work, we propose an evaluation protocol to systematically test how the RAG system handles conflicts between parametric knowledge and evidence retrieved from context with varying amounts of misleading information. We target correct answers to factoid questions that the model responds to correctly, even when there is no retrieval, and use this to test the system with clean, poisoned, and mixed evidence. The proposed analytical framework combines parametric override and confidence metrics to assess when and how misleading information affects the generation process of LLMs. This study aims to provide insights into the robustness of RAG systems in information disorder scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 21 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

16 of 21 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Uncertainty Quantification for Retrieval-Augmented Reasoning13 Oct

Other references · 15

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  6. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  8. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  9. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
  10. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  11. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 267
  12. 2024BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Modelscited by 86
3 more
  1. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 30
  2. 2025ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checkingcited by 10
  3. 2025POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Modelscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
  2. 2026ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation
  3. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence
  4. 2024Retrieval-Augmented Generation with Estimation of Source Reliability
  5. 2026RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation
  6. 2025Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization
  7. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
  8. 2026A Hierarchical Consistency Framework for Auditing Retrieval-Augmented Generation Systems