mlsanityData to 7 Oct 2026

Making Retrieval-Augmented Language Models Robust to Irrelevant Context

arXiv 2310.01558 ↗First posted 2 Oct 2023cs.CL cs.AIcited by 364

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

Abstract (arXiv)

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance when it is relevant, and does not harm performance when it is not. This is particularly important in multi-hop reasoning scenarios, where misuse of irrelevant evidence can lead to cascading errors. However, recent work has shown that retrieval augmentation can sometimes have a negative effect on performance. In this work, we present a thorough analysis on five open-domain question answering benchmarks, characterizing cases when retrieval reduces accuracy. We then propose two methods to mitigate this issue. First, a simple baseline that filters out retrieved passages that do not entail question-answer pairs according to a natural language inference (NLI) model. This is effective in preventing performance reduction, but at a cost of also discarding relevant passages. Thus, we propose a method for automatically generating data to fine-tune the language model to properly leverage retrieved passages, using a mix of relevant and irrelevant contexts at training time. We empirically show that even 1,000 examples suffice to train the model to be robust to irrelevant contexts while maintaining high performance on examples with relevant ones.

Key facts. Cited by 364 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 47 of its 57 references that are in the map. First posted on arXiv 2 Oct 2023.

Builds on

47 of 57 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval23 Jun
  2. 2023Active Retrieval Augmented Generation11 May
  3. 2023In-Context Retrieval-Augmented Language Models31 Jan
  4. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP28 Dec
  5. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories20 Dec
  6. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Training10 Feb

Other references · 39

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  8. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  9. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  10. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  11. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
27 more
  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  2. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  3. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  4. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  5. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  6. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  7. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  8. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  9. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  10. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 292
  11. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 290
  12. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 240
  13. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 238
  14. 2017Constructing Datasets for Multi-hop Reading Comprehension Across Documentscited by 190
  15. 2020How Context Affects Language Models' Factual Predictionscited by 181
  16. 2022Large Language Models with Controllable Working Memorycited by 169
  17. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  18. 2020Break It Down: A Question Understanding Benchmarkcited by 131
  19. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 108
  20. 2022Capturing Failures of Large Language Models via Human Cognitive Biasescited by 97
  21. 2022DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answeringcited by 93
  22. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  23. 2023Context-faithful Prompting for Large Language Modelscited by 76
  24. 2022Entity Cloze By Date: What LMs Know About Unseen Entitiescited by 55
  25. 2021Sorting through the noise: Testing robustness of information processing in pre-trained language modelscited by 27
  26. 2021How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AIcited by 22
  27. 2022COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Modelscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 118; 2025: 124; 2026: 111.

364 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  3. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  4. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  5. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  6. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 251
  7. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  8. 2024Corrective Retrieval Augmented Generationcited by 187
  9. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  10. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  11. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 165
  12. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?cited by 155
38 more
  1. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
  2. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 122
  3. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 100
  4. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  5. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  6. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 88
  7. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  8. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 76
  9. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  10. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
  11. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systemscited by 69
  12. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  13. 2024Inference Scaling for Long-Context Retrieval Augmented Generationcited by 65
  14. 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbationscited by 64
  15. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 57
  16. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  17. 2023RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledgecited by 51
  18. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  19. 2024Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?cited by 47
  20. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  21. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  22. 2024What is the Role of Small Models in the LLM Era: A Surveycited by 41
  23. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Modelscited by 41
  24. 2024Training Language Models to Generate Text with Citations via Fine-grained Rewardscited by 40
  25. 2024GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Modelcited by 40
  26. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  27. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  28. 2026Dr. Zero: Self-Evolving Search Agents without Training Datacited by 39
  29. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  30. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  31. 2024Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refusecited by 33
  32. 2024RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysiscited by 33
  33. 2024JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capabilitycited by 32
  34. 2025The Distracting Effect: Understanding Irrelevant Passages in RAGcited by 32
  35. 2025R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learningcited by 32
  36. 2023Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Trainingcited by 31
  37. 2024How Much Can RAG Help the Reasoning of LLM?cited by 31
  38. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29

50 most cited of 364 All 364 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Structured Relevance Assessment for Robust Retrieval-Augmented Language Models
  2. 2025Do Retrieval-Augmented Language Models Adapt to Varying User Needs?
  3. 2023RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
  4. 2023BRENT: Bidirectional Retrieval Enhanced Norwegian Transformer
  5. 2025Improving Context Fidelity via Native Retrieval-Augmented Reasoning
  6. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model
  7. 2025Studying the Role of Input-Neighbor Overlap in Retrieval-Augmented Language Models Training Efficiency
  8. 2022QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation