mlsanityData to 7 Oct 2026

Entity-Based Knowledge Conflicts in Question Answering

arXiv 2109.05052 ↗First posted 10 Sep 2021cs.CL cs.LGcited by 349

Not on the map. Why?

Cited by 83 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Knowledge-dependent tasks typically use two sources of knowledge: parametric, learned at training time, and contextual, given as a passage at inference time. To understand how models use these sources together, we formalize the problem of knowledge conflicts, where the contextual information contradicts the learned information. Analyzing the behaviour of popular models, we measure their over-reliance on memorized information (the cause of hallucinations), and uncover important factors that exacerbate this behaviour. Lastly, we propose a simple method to mitigate over-reliance on parametric knowledge, which minimizes hallucination, and improves out-of-distribution generalization by 4%-7%. Our findings demonstrate the importance for practitioners to evaluate model tendency to hallucinate rather than read, and show that our mitigation strategy encourages generalization to evolving information (i.e., time-dependent queries). To encourage these practices, we have released our framework for generating knowledge conflicts.

Key facts. Cited by 349 papers in the map (data through 7 Oct 2026). Builds on 25 of its 38 references that are in the map. First posted on arXiv 10 Sep 2021.

Builds on

25 of 38 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2019Language Models as Knowledge Bases?cited by 1,922
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  10. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  11. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  12. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 428
13 more
  1. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  2. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
  3. 2019MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehensioncited by 183
  4. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  5. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  6. 2020"You are grounded!": Latent Name Artifacts in Pre-trained Language Modelscited by 39
  7. 2021Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLPcited by 30
  8. 2018Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Modelscited by 25
  9. 2017Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Taskcited by 24
  10. 2019An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answeringcited by 22
  11. 2021Self-Supervised Test-Time Learning for Reading Comprehensioncited by 22
  12. 2020Entity-Switched Datasets: An Approach to Auditing the In-Domain Robustness of Named Entity Recognition Modelscited by 12
  13. 2019Improving Generalization in Coreference Resolution via Adversarial Trainingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 21; 2023: 51; 2024: 93; 2025: 70; 2026: 108.

349 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  3. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  4. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  5. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  6. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  7. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  8. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  9. 2023Tool Learning with Foundation Modelscited by 302
  10. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  11. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  12. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 272
38 more
  1. 2022Prompting GPT-3 To Be Reliablecited by 258
  2. 2022RealTime QA: What's the Answer Right Now?cited by 239
  3. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  4. 2023A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicitycited by 180
  5. 2021Towards Continual Knowledge Learning of Language Modelscited by 172
  6. 2022Large Language Models with Controllable Working Memorycited by 169
  7. 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 146
  8. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  9. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  10. 2023On the Risk of Misinformation Pollution with Large Language Modelscited by 124
  11. 2024To Believe or Not to Believe Your LLMcited by 120
  12. 2022TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Modelscited by 117
  13. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidencecited by 109
  14. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 98
  15. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  16. 2022DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answeringcited by 93
  17. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 93
  18. 2024Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Modelscited by 87
  19. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 85
  20. 2023Context-faithful Prompting for Large Language Modelscited by 76
  21. 2023In-context Pretraining: Language Modeling Beyond Document Boundariescited by 76
  22. 2023Exposing Attention Glitches with Flip-Flop Language Modelingcited by 74
  23. 2024What Evidence Do Language Models Find Convincing?cited by 74
  24. 2023Large Language Models can Learn Rulescited by 66
  25. 2024Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineeringcited by 60
  26. 2025Retrieval-Augmented Generation with Conflicting Evidencecited by 60
  27. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 57
  28. 2023PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptionscited by 53
  29. 2024Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?cited by 53
  30. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noisecited by 52
  31. 2024Context-DPO: Aligning Language Models for Context-Faithfulnesscited by 50
  32. 2023Resolving Knowledge Conflicts in Large Language Modelscited by 49
  33. 2024Enhancing Contextual Understanding in Large Language Models through Contrastive Decodingcited by 49
  34. 2023Understanding Retrieval Augmentation for Long-Form Question Answeringcited by 45
  35. 2024Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Modelscited by 44
  36. 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understandingcited by 44
  37. 2023Meta-Learning Online Adaptation of Language Modelscited by 43
  38. 2024WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipediacited by 43

50 most cited of 349 All 349 (JSON)