mlsanityData to 7 Oct 2026

Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey

arXiv 2601.19927 ↗First posted 10 Jan 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → Hallucination detection in RAG

Abstract (arXiv)

Large Language Models (LLMs)-based question answering (QA) systems play a critical role in modern AI, demonstrating strong performance across various tasks. However, LLM-generated responses often suffer from hallucinations, unfaithful statements lacking reliable references. Retrieval-Augmented Generation (RAG) frameworks enhance LLM responses by incorporating external references but also introduce new forms of hallucination due to complex interactions between the retriever and generator. To address these challenges, researchers have explored attribution-based techniques that ensure responses are verifiably supported by retrieved content. Despite progress, a unified pipeline for these techniques, along with a clear taxonomy and systematic comparison of their strengths and weaknesses, remains lacking. A well-defined taxonomy is essential for identifying specific failure modes within RAG systems, while comparative analysis helps practitioners choose appropriate solutions based on hallucination types and application context. This survey investigates how attribution-based techniques are used within RAG systems to mitigate hallucinations and addresses the gap by: (i) outlining a taxonomy of hallucination types in RAG systems, (ii) presenting a unified pipeline for attribution techniques, (iii) reviewing techniques based on the hallucinations they target, and (iv) discussing strengths and weaknesses with practical guidelines. This work offers insights for future research and practical use of attribution techniques in RAG systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Hallucination detection in RAG, one of 15 directions in Retrieval-augmented generation. Builds on 72 of its 88 references that are in the map. First posted on arXiv 10 Jan 2026.

Builds on

72 of 88 references.

References · 72

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  9. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  11. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
38 more
  1. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  2. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  3. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  4. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  5. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  6. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 399
  7. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  8. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  9. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  10. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  11. 2022Teaching language models to support answers with verified quotescited by 290
  12. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  13. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 266
  14. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  15. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  16. 2023Query2doc: Query Expansion with Large Language Modelscited by 146
  17. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  18. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  19. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  20. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
  21. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 78
  22. 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 74
  23. 2023Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Taskscited by 73
  24. 2023Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-Incited by 71
  25. 2023A Survey of Large Language Models Attributioncited by 71
  26. 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directionscited by 69
  27. 2022Recitation-Augmented Language Modelscited by 65
  28. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  29. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  30. 2020Evidence-based Factual Error Correctioncited by 44
  31. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  32. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 44
  33. 2024Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigationcited by 43
  34. 2023"According to ...": Prompting Language Models Improves Quoting from Pre-Training Datacited by 42
  35. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 42
  36. 2023PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adaptercited by 38
  37. 2023Augmented Large Language Models with Parametric Knowledge Guidingcited by 37
  38. 2025AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decaycited by 36

50 most cited of 72 All 72 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
  2. 2024Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination
  3. 2025Towards Lighter and Robust Evaluation for Retrieval Augmented Generation
  4. 2024100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo
  5. 2025Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables
  6. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
  7. 2024ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions
  8. 2024RAGged Edges: The Double-Edged Sword of Retrieval-Augmented Chatbots