mlsanityData to 14 Oct 2026

Knowledge Conflicts for LLMs: A Survey

arXiv 2403.08319 ↗First posted 13 Mar 2024cs.CL cs.AI cs.IRcited by 283

Not on the map. Why?

Cited by 70 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and reviewing available solutions, this survey aims to shed light on strategies for improving the robustness of LLMs, thereby serving as a valuable resource for advancing research in this evolving area.

Key facts. Cited by 283 papers in the map (data through 14 Oct 2026). Builds on 142 of its 201 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

142 of 201 references.

References · 142

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  8. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  9. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  10. 2016Pointer Sentinel Mixture Modelscited by 3,096
  11. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  12. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
38 more
  1. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  2. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  3. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  7. 2019Language Models as Knowledge Bases?cited by 1,936
  8. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  9. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  10. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
  11. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  12. 2018Hierarchical Neural Story Generationcited by 1,193
  13. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  14. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  15. 2023LIMA: Less Is More for Alignmentcited by 1,100
  16. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  17. 2015Teaching Machines to Read and Comprehendcited by 1,049
  18. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  19. 2021Ethical and social risks of harm from Language Modelscited by 966
  20. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  21. 2020A Primer in BERTology: What we know about how BERT workscited by 815
  22. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  23. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  24. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  25. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  26. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  27. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 616
  28. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
  29. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  30. 2017The NarrativeQA Reading Comprehension Challengecited by 597
  31. 2021Editing Factual Knowledge in Language Modelscited by 553
  32. 2021Fast Model Editing at Scalecited by 498
  33. 2021A Survey on Automated Fact-Checkingcited by 378
  34. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
  35. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  36. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  37. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
  38. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 341

50 most cited of 142 All 142 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 40; 2025: 111; 2026: 132.

283 papers.

Sort:

By area:

  1. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  3. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 121
  4. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 101
  5. 2024Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communitiescited by 86
  6. 2025SealQA: Raising the Bar for Reasoning in Search-Augmented Language Modelscited by 75
  7. 2024On the Role of Attention Heads in Large Language Model Safetycited by 72
  8. 2024Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineeringcited by 63
  9. 2025Retrieval-Augmented Generation with Conflicting Evidencecited by 63
  10. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 58
  11. 2024Knowledge Mechanisms in Large Language Models: A Survey and Perspectivecited by 51
  12. 2025Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Surveycited by 51
38 more
  1. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  2. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  3. 2026STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?cited by 50
  4. 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understandingcited by 47
  5. 2025Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Modelscited by 39
  6. 2024IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neuronscited by 38
  7. 2024Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMscited by 38
  8. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  9. 2024Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMscited by 33
  10. 2025Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agentscited by 33
  11. 2024Long2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recallcited by 32
  12. 2025SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Modelcited by 32
  13. 2025Taming Knowledge Conflicts in Language Modelscited by 30
  14. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 29
  15. 2024Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Modelscited by 28
  16. 2025FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generationcited by 28
  17. 2024Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documentscited by 27
  18. 2025DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMscited by 25
  19. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 24
  20. 2024KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Modelscited by 20
  21. 2024Retrieval-Augmented Generation with Estimation of Source Reliabilitycited by 19
  22. 2025Benchmarking Multimodal Knowledge Conflict for Large Multimodal Modelscited by 19
  23. 2024Correctness is not Faithfulness in RAG Attributionscited by 18
  24. 2025Robust Multimodal Large Language Models Against Modality Conflictcited by 18
  25. 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Searchcited by 18
  26. 2024Analysing the Residual Stream of Language Models Under Knowledge Conflictscited by 17
  27. 2025Tool Unlearning for Tool-Augmented LLMscited by 17
  28. 2026HorizonBench: Long-Horizon Personalization with Evolving Preferencescited by 17
  29. 2025LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Datacited by 16
  30. 2025Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflictcited by 16
  31. 2024Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Modelscited by 15
  32. 2026Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflictcited by 15
  33. 2026MemTX: Transactional Belief Commit for Stateful Agent Memorycited by 15
  34. 2025Can Language Models Follow Multiple Turns of Entangled Instructions?cited by 14
  35. 2025Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Deliverycited by 14
  36. 2025GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agentscited by 14
  37. 2024UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Modelscited by 13
  38. 2025Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactionscited by 13

50 most cited of 283 All 283 (JSON)