mlsanityData to 14 Oct 2026

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

arXiv 2212.10511 ↗First posted 20 Dec 2022cs.CL cs.AI cs.LGcited by 1,128

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

Abstract (arXiv)

Despite their impressive performance on diverse tasks, large language models (LMs) still struggle with tasks requiring rich world knowledge, implying the limitations of relying solely on their parameters to encode a wealth of world knowledge. This paper aims to understand LMs' strengths and limitations in memorizing factual knowledge, by conducting large-scale knowledge probing experiments of 10 models and 4 augmentation methods on PopQA, our new open-domain QA dataset with 14k questions. We find that LMs struggle with less popular factual knowledge, and that scaling fails to appreciably improve memorization of factual knowledge in the long tail. We then show that retrieval-augmented LMs largely outperform orders of magnitude larger LMs, while unassisted LMs remain competitive in questions about high-popularity entities. Based on those findings, we devise a simple, yet effective, method for powerful and efficient retrieval-augmented LMs, which retrieves non-parametric memories only when necessary. Experimental results show that this significantly improves models' performance while reducing the inference costs.

Key facts. Cited by 1,128 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 37 of its 47 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

37 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Models5 Aug
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  7. 2019Language Models as Knowledge Bases?cited by 1,936
  8. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  9. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  10. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  11. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
23 more
  1. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  2. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  3. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  4. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  5. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 713
  6. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  7. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  8. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  9. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  10. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  11. 2022RealTime QA: What's the Answer Right Now?cited by 244
  12. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 200
  13. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 144
  14. 2022Impact of Pretraining Term Frequencies on Few-Shot Reasoningcited by 142
  15. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  16. 2022TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Modelscited by 119
  17. 2021Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Basescited by 107
  18. 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
  19. 2019E-BERT: Efficient-Yet-Effective Entity Embeddings for BERTcited by 96
  20. 2021Efficient Nearest Neighbor Language Modelscited by 93
  21. 2022Recitation-Augmented Language Modelscited by 65
  22. 2021Evidentiality-guided Generation for Knowledge-Intensive NLP Taskscited by 40
  23. 2022You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LMcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 68; 2024: 289; 2025: 321; 2026: 450.

1,128 papers.

Sort:

By area:

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  3. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,786
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  5. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  6. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 830
  7. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  8. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 497
  9. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  10. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 418
  11. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  12. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
38 more
  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  2. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  3. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  4. 2024Humans or LLMs as the Judge? A Study on Judgement Biasescited by 323
  5. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  6. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  7. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 278
  8. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  9. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  10. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 242
  11. 2024Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Modelscited by 235
  12. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  13. 2024Tool Learning with Large Language Models: A Surveycited by 223
  14. 2023Fine-tuning Language Models for Factualitycited by 221
  15. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  16. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  17. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  18. 2023FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setscited by 201
  19. 2024Corrective Retrieval Augmented Generationcited by 197
  20. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  21. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  22. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  23. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  24. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 168
  25. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
  26. 2024Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokenscited by 153
  27. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 151
  28. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 150
  29. 2025RewardBench 2: Advancing Reward Model Evaluationcited by 150
  30. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  31. 2024How to Train Long-Context Language Models (Effectively)cited by 146
  32. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 142
  33. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 137
  34. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 128
  35. 2024HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughlycited by 125
  36. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 124
  37. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 121
  38. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 118

50 most cited of 1,128 All 1,128 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs
  2. 2024Disentangling Memory and Reasoning Ability in Large Language Models
  3. 2026REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
  4. 2025Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
  5. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
  6. 2025MLP Memory: A Retriever-Pretrained Memory for Large Language Models
  7. 2026Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory
  8. 2024Learning and Unlearning of Fabricated Knowledge in Language Models