mlsanityData to 14 Oct 2026

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

arXiv 2305.13300 ↗First posted 22 May 2023cs.CL cs.AIcited by 341

Not on the map. Why?

Cited by 99 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

By providing external information to large language models (LLMs), tool augmentation (including retrieval augmentation) has emerged as a promising solution for addressing the limitations of LLMs' static parametric memory. However, how receptive are LLMs to such external evidence, especially when the evidence conflicts with their parametric memory? We present the first comprehensive and controlled investigation into the behavior of LLMs when encountering knowledge conflicts. We propose a systematic framework to elicit high-quality parametric memory from LLMs and construct the corresponding counter-memory, which enables us to conduct a series of controlled experiments. Our investigation reveals seemingly contradicting behaviors of LLMs. On the one hand, different from prior wisdom, we find that LLMs can be highly receptive to external evidence even when that conflicts with their parametric memory, given that the external evidence is coherent and convincing. On the other hand, LLMs also demonstrate a strong confirmation bias when the external evidence contains some information that is consistent with their parametric memory, despite being presented with conflicting evidence at the same time. These results pose important implications that are worth careful consideration for the further development and deployment of tool- and retrieval-augmented LLMs. Resources are available at https://github.com/OSU-NLP-Group/LLM-Knowledge-Conflict.

Key facts. Cited by 341 papers in the map (data through 14 Oct 2026). Builds on 59 of its 74 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

59 of 74 references.

References · 59

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  9. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  10. 2020Extracting Training Data from Large Language Modelscited by 2,189
  11. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  12. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
38 more
  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2019Language Models as Knowledge Bases?cited by 1,936
  3. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  4. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  5. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  7. 2023PaLM 2 Technical Reportcited by 1,162
  8. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  9. 2022Mass-Editing Memory in a Transformercited by 1,001
  10. 2019How Can We Know What Language Models Know?cited by 959
  11. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  12. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  13. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  14. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  15. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  16. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  17. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  18. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  19. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  20. 2021Knowledge Neurons in Pretrained Transformerscited by 601
  21. 2021Editing Factual Knowledge in Language Modelscited by 553
  22. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  23. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  24. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 356
  25. 2023Tool Learning with Foundation Modelscited by 302
  26. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  27. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  28. 2022Prompting GPT-3 To Be Reliablecited by 260
  29. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
  30. 2020How Context Affects Language Models' Factual Predictionscited by 181
  31. 2021Counterfactual Memorization in Neural Language Modelscited by 156
  32. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 144
  33. 2022StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Modelscited by 126
  34. 2022Training Language Models with Memory Augmentationcited by 113
  35. 2020Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Modelscited by 110
  36. 2021Time Waits for No One! Analysis and Challenges of Temporal Misalignmentcited by 91
  37. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 85
  38. 2023Context-faithful Prompting for Large Language Modelscited by 80

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 14; 2024: 100; 2025: 87; 2026: 140.

341 papers.

Sort:

By area:

  1. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  2. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  3. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  4. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  5. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 274
  6. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  7. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 229
  8. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  9. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  10. 2024When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboardscited by 137
  11. 2023LawBench: Benchmarking Legal Knowledge of Large Language Modelscited by 117
  12. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidencecited by 113
38 more
  1. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 109
  2. 2024Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Codecited by 107
  3. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 93
  4. 2025HalluLens: LLM Hallucination Benchmarkcited by 92
  5. 2024Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Modelscited by 91
  6. 2025Words or Vision: Do Vision-Language Models Have Blind Faith in Text?cited by 89
  7. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 86
  8. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  9. 2024What Evidence Do Language Models Find Convincing?cited by 75
  10. 2025SealQA: Raising the Bar for Reasoning in Search-Augmented Language Modelscited by 75
  11. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systemscited by 72
  12. 2024Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineeringcited by 63
  13. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 58
  14. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  15. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  16. 2024Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?cited by 48
  17. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  18. 2024WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipediacited by 44
  19. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Modelscited by 43
  20. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
  21. 2025Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Modelscited by 39
  22. 2024Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMscited by 38
  23. 2023When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Taskscited by 37
  24. 2024AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledgecited by 37
  25. 2024DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Modelscited by 34
  26. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  27. 2025Evaluating and Steering Modality Preferences in Multimodal Large Language Modelcited by 33
  28. 2023MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Followingcited by 30
  29. 2025Taming Knowledge Conflicts in Language Modelscited by 30
  30. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 29
  31. 2023ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attackscited by 28
  32. 2024Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Modelscited by 28
  33. 2025Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievalscited by 28
  34. 2025FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generationcited by 28
  35. 2024HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wildcited by 27
  36. 2024Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documentscited by 27
  37. 2024Context versus Prior Knowledge in Language Modelscited by 26
  38. 2024To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contextscited by 25

50 most cited of 341 All 341 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts
  2. 2024Disentangling Memory and Reasoning Ability in Large Language Models
  3. 2026Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
  4. 2025Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild
  5. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
  6. 2024Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
  7. 2026MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
  8. 2026STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?