mlsanityData to 7 Oct 2026

A Comprehensive Study of Knowledge Editing for Large Language Models

arXiv 2401.01286 ↗First posted 2 Jan 2024cs.CL cs.AI cs.CVcited by 157

Not on the map. Why?

Cited by 21 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training, arising from their extensive parameterization. This challenge is further intensified by the dynamic nature of the world, necessitating frequent updates to LLMs to correct outdated information or integrate new knowledge, thereby ensuring their continued relevance. Note that many applications demand continual model adjustments post-training to address deficiencies or undesirable behaviors. There is an increasing interest in efficient, lightweight methods for on-the-fly model modifications. To this end, recent years have seen a burgeoning in the techniques of knowledge editing for LLMs, which aim to efficiently modify LLMs' behaviors within specific domains while preserving overall performance across various inputs. In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches. Drawing inspiration from educational and cognitive research theories, we propose a unified categorization criterion that classifies knowledge editing methods into three groups: resorting to external knowledge, merging knowledge into the model, and editing intrinsic knowledge. Furthermore, we introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches. Additionally, we provide an in-depth analysis of knowledge location, which can give a deeper understanding of the knowledge structures inherent within LLMs. Finally, we discuss several potential applications of knowledge editing, outlining its broad and impactful implications.

Key facts. Cited by 157 papers in the map (data through 7 Oct 2026). Builds on 202 of its 244 references that are in the map. First posted on arXiv 2 Jan 2024.

Builds on

202 of 244 references.

References · 202

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  9. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  10. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  11. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  12. 2022Locating and Editing Factual Associations in GPTcited by 2,609
38 more
  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2022Emergent Abilities of Large Language Modelscited by 2,483
  3. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2019Language Models as Knowledge Bases?cited by 1,922
  7. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  10. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  11. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  12. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  13. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  14. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  15. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  16. 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,130
  17. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  18. 2022Editing Models with Task Arithmeticcited by 1,076
  19. 2018Experience Replay for Continual Learningcited by 1,074
  20. 2022Mass-Editing Memory in a Transformercited by 976
  21. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  22. 2023A Survey on Multimodal Large Language Modelscited by 898
  23. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  24. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  25. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  26. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  27. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  28. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  29. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 700
  30. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  31. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  32. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  33. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  34. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  35. 2021Editing Factual Knowledge in Language Modelscited by 548
  36. 2023Erasing Concepts from Diffusion Modelscited by 530
  37. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 525
  38. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 522

50 most cited of 202 All 202 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 57; 2025: 59; 2026: 41.

157 papers.

Sort:

By area:

  1. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  2. 2024TOFU: A Task of Fictitious Unlearning for LLMscited by 507
  3. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  4. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  5. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  6. 2024Continual Learning with Pre-Trained Models: A Surveycited by 151
  7. 2025MemOS: A Memory OS for AI Systemcited by 129
  8. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  9. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  10. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  11. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 101
  12. 2024WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Modelscited by 90
38 more
  1. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  2. 2024Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communitiescited by 84
  3. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 70
  4. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelscited by 68
  5. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 65
  6. 2024Knowledge Circuits in Pretrained Transformerscited by 60
  7. 2024A Unified Framework for Model Editingcited by 54
  8. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  9. 2024Larimar: Large Language Models with Episodic Memory Controlcited by 53
  10. 2024Understanding and Patching Compositional Reasoning in LLMscited by 45
  11. 2024To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Modelscited by 42
  12. 2024Multi-hop Question Answering under Temporal Knowledge Editingcited by 36
  13. 2024Locate-then-edit for Multi-hop Factual Recall under Knowledge Editingcited by 36
  14. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  15. 2024MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memorycited by 35
  16. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 33
  17. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmarkcited by 30
  18. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  19. 2024Perturbation-Restrained Sequential Model Editingcited by 27
  20. 2025WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMscited by 25
  21. 2025The Mirage of Model Editing: Revisiting Evaluation in the Wildcited by 24
  22. 2024Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agendacited by 22
  23. 2024Can Editing LLMs Inject Harm?cited by 22
  24. 2024Locking Down the Finetuned LLMs Safetycited by 22
  25. 2025Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMscited by 22
  26. 2024Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Modelscited by 20
  27. 2024RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuningcited by 20
  28. 2024Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Modelscited by 18
  29. 2024Towards Unified Multimodal Editing with Enhanced Knowledge Collaborationcited by 18
  30. 2024Neuron-Level Sequential Editing for Large Language Modelscited by 18
  31. 2024Should We Really Edit Language Models? On the Evaluation of Edited Language Modelscited by 18
  32. 2024Agents for self-driving laboratories applied to quantum computingcited by 18
  33. 2025Large language models for artificial general intelligence (AGI): A survey of foundational principles and approachescited by 18
  34. 2024InstructEdit: Instruction-based Knowledge Editing for Large Language Modelscited by 17
  35. 2024Knowledge Editing in Language Models via Adapted Direct Preference Optimizationcited by 17
  36. 2025Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuningcited by 17
  37. 2024On Catastrophic Inheritance of Large Foundation Modelscited by 15
  38. 2024Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorizationcited by 15

50 most cited of 157 All 157 (JSON)