mlsanityData to 14 Oct 2026

Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models

arXiv 2311.09210 ↗First posted 15 Nov 2023cs.CL cs.AIcited by 184

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Retrieval-augmented language models (RALMs) represent a substantial advancement in the capabilities of large language models, notably in reducing factual hallucination by leveraging external knowledge sources. However, the reliability of the retrieved information is not always guaranteed. The retrieval of irrelevant data can lead to misguided responses, and potentially causing the model to overlook its inherent knowledge, even when it possesses adequate information to address the query. Moreover, standard RALMs often struggle to assess whether they possess adequate knowledge, both intrinsic and retrieved, to provide an accurate answer. In situations where knowledge is lacking, these systems should ideally respond with "unknown" when the answer is unattainable. In response to these challenges, we introduces Chain-of-Noting (CoN), a novel approach aimed at improving the robustness of RALMs in facing noisy, irrelevant documents and in handling unknown scenarios. The core idea of CoN is to generate sequential reading notes for retrieved documents, enabling a thorough evaluation of their relevance to the given question and integrating this information to formulate the final answer. We employed ChatGPT to create training data for CoN, which was subsequently trained on an LLaMa-2 7B model. Our experiments across four open-domain QA benchmarks show that RALMs equipped with CoN significantly outperform standard RALMs. Notably, CoN achieves an average improvement of +7.9 in EM score given entirely noisy retrieved documents and +10.5 in rejection rates for real-time questions that fall outside the pre-training knowledge scope.

Key facts. Cited by 184 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 43 of its 53 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

43 of 53 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Context2 Oct
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Models30 Jan
  3. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories20 Dec
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Training10 Feb

Other references · 37

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  11. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  12. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
25 more
  1. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  2. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  3. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  4. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 530
  5. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 488
  6. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 413
  7. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  8. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
  9. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 318
  10. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  11. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 296
  12. 2022RealTime QA: What's the Answer Right Now?cited by 244
  13. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  14. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  15. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  16. 2020A Survey of Knowledge-Enhanced Text Generationcited by 120
  17. 2022Training Language Models with Memory Augmentationcited by 113
  18. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  19. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  20. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Promptingcited by 77
  21. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 67
  22. 2022Questions Are All You Need to Train a Dense Passage Retrievercited by 47
  23. 2021UnitedQA: A Hybrid Approach for Open Domain Question Answeringcited by 42
  24. 2022Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speechcited by 25
  25. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 72; 2025: 57; 2026: 49.

184 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  3. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  4. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 431
  5. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 260
  6. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  7. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  8. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  9. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 150
  10. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  11. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 142
  12. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
38 more
  1. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 105
  2. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 89
  3. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  4. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  5. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  6. 2024KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generationcited by 67
  7. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  8. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generationcited by 64
  9. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 58
  10. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  11. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  12. 2024DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literaturecited by 50
  13. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 49
  14. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 49
  15. 2024Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?cited by 48
  16. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  17. 2024RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedbackcited by 46
  18. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  19. 2024Is Semantic Chunking Worth the Computational Cost?cited by 43
  20. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Modelscited by 43
  21. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 42
  22. 2024LumberChunker: Long-Form Narrative Document Segmentationcited by 36
  23. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 36
  24. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  25. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  26. 2025The Distracting Effect: Understanding Irrelevant Passages in RAGcited by 33
  27. 2024PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agentscited by 30
  28. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answeringcited by 28
  29. 2024Improving Retrieval Augmented Language Model with Self-Reasoningcited by 28
  30. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  31. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domainscited by 28
  32. 2025SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinementcited by 28
  33. 2025SciSciGPT: Advancing Human-AI Collaboration in the Science of Sciencecited by 27
  34. 2024Making Long-Context Language Models Better Multi-Hop Reasonerscited by 26
  35. 2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responsescited by 25
  36. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 24
  37. 2024RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignmentcited by 23
  38. 2023Towards Verifiable Text Generation with Evolving Memory and Self-Reflectioncited by 21

50 most cited of 184 All 184 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Structured Relevance Assessment for Robust Retrieval-Augmented Language Models
  2. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing
  3. 2023RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
  4. 2023In-Context Retrieval-Augmented Language Models
  5. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise
  6. 2025Know Or Not: a library for evaluating out-of-knowledge base robustness
  7. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  8. 2024FlashBack: Efficient Retrieval-Augmented Language Modeling for Fast Inference