mlsanityData to 7 Oct 2026

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models

arXiv 2308.07269 ↗First posted 14 Aug 2023cs.CL cs.AI cs.CVcited by 97

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing approaches for LLMs have emerged -- aiming to subtly inject/edit updated knowledge or adjust undesired behavior while minimizing the impact on unrelated inputs. Nevertheless, due to significant differences among various knowledge editing methods and the variations in task setups, there is no standard implementation framework available for the community, which hinders practitioners from applying knowledge editing to applications. To address these issues, we propose EasyEdit, an easy-to-use knowledge editing framework for LLMs. It supports various cutting-edge knowledge editing approaches and can be readily applied to many well-known LLMs such as T5, GPT-J, LlaMA, etc. Empirically, we report the knowledge editing results on LlaMA-2 with EasyEdit, demonstrating that knowledge editing surpasses traditional fine-tuning in terms of reliability and generalization. We have released the source code on GitHub, along with Google Colab tutorials and comprehensive documentation for beginners to get started. Besides, we present an online system for real-time knowledge editing, and a demo video.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). Builds on 45 of its 70 references that are in the map. First posted on arXiv 14 Aug 2023.

Builds on

45 of 70 references.

References · 45

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  8. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  9. 2023A Survey of Large Language Modelscited by 2,537
  10. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  12. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
33 more
  1. 2019Language Models as Knowledge Bases?cited by 1,922
  2. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  3. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  4. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  5. 2023PaLM 2 Technical Reportcited by 1,154
  6. 2022Mass-Editing Memory in a Transformercited by 976
  7. 2019How Can We Know What Language Models Know?cited by 953
  8. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  9. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  10. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  11. 2021Editing Factual Knowledge in Language Modelscited by 548
  12. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 522
  13. 2023Dissecting Recall of Factual Associations in Auto-Regressive Language Modelscited by 512
  14. 2022Memory-Based Model Editing at Scalecited by 443
  15. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  16. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  17. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  18. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 284
  19. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
  20. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  21. 2023Challenges and Applications of Large Language Modelscited by 251
  22. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 238
  23. 2023Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Modelscited by 237
  24. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 226
  25. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  26. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 196
  27. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  28. 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 179
  29. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  30. 2023Inspecting and Editing Knowledge Representations in Language Modelscited by 140
  31. 2018Generating Informative and Diverse Conversational Responses via Adversarial Information Maximizationcited by 114
  32. 2022Retrieval Augmentation for Commonsense Reasoning: A Unified Approachcited by 14
  33. 2023AsdKB: A Chinese Knowledge Base for the Early Screening and Diagnosis of Autism Spectrum Disordercited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 28; 2025: 35; 2026: 27.

97 papers.

Sort:

By area:

  1. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  2. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  3. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 101
  4. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
  5. 2024Knowledge Circuits in Pretrained Transformerscited by 60
  6. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  7. 2024Larimar: Large Language Models with Episodic Memory Controlcited by 53
  8. 2023Can Language Models be Instructed to Protect Personal Information?cited by 46
  9. 2023Can We Edit Multimodal Large Language Models?cited by 44
  10. 2024WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editingcited by 40
  11. 2024Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Factscited by 36
  12. 2023Evaluating the Reversal Curse in Model Editingcited by 34
38 more
  1. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmarkcited by 30
  2. 2024Perturbation-Restrained Sequential Model Editingcited by 27
  3. 2024Knowledge Editing through Chain-of-Thoughtcited by 26
  4. 2024Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?cited by 24
  5. 2025The Mirage of Model Editing: Revisiting Evaluation in the Wildcited by 24
  6. 2023Editing Personality for Large Language Modelscited by 22
  7. 2024Can Editing LLMs Inject Harm?cited by 22
  8. 2024Configurable Foundation Models: Building LLMs from a Modular Perspectivecited by 22
  9. 2024Locking Down the Finetuned LLMs Safetycited by 22
  10. 2024Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Modelscited by 18
  11. 2024InstructEdit: Instruction-based Knowledge Editing for Large Language Modelscited by 17
  12. 2025Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuningcited by 17
  13. 2025Position: Editing Large Language Models Poses Serious Safety Riskscited by 15
  14. 2023Large Knowledge Model: Perspectives and Challengescited by 12
  15. 2024AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deploymentcited by 12
  16. 2023Cross-Lingual Knowledge Editing in Large Language Modelscited by 11
  17. 2024MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Modelscited by 11
  18. 2024Neighboring Perturbations of Knowledge Editing on Large Language Modelscited by 10
  19. 2025Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subjectcited by 10
  20. 2025MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMscited by 10
  21. 2024Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Modelscited by 9
  22. 2025Fine-tuning Done Right in Model Editingcited by 9
  23. 2024Model Editing for LLMs4Code: How Far are We?cited by 8
  24. 2025Knowledge Fusion of Large Language Models Via Modular SkillPackscited by 8
  25. 2024ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domainscited by 7
  26. 2025Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injectioncited by 7
  27. 2025Tracing and Reversing Edits in LLMscited by 7
  28. 2025Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMscited by 7
  29. 2024Towards Trustable Language Models: Investigating Information Quality of Large Language Modelscited by 6
  30. 2025Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editingcited by 6
  31. 2025Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trustcited by 6
  32. 2025Is Model Editing Built on Sand? Revealing Its Illusory Success and Fragile Foundationcited by 6
  33. 2024Can LLMs be Fooled? Investigating Vulnerabilities in LLMscited by 5
  34. 2025DualEdit: Dual Editing for Knowledge Updating in Vision-Language Modelscited by 5
  35. 2025SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Modelscited by 5
  36. 2024Composable Interventions for Language Modelscited by 4
  37. 2024Resolving Lexical Bias in Model Editingcited by 4
  38. 2025Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QAcited by 4

50 most cited of 97 All 97 (JSON)