mlsanityData to 7 Oct 2026

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

arXiv 2211.11031 ↗First posted 20 Nov 2022cs.LGcited by 267

Not on the map. Why?

Abstract (arXiv)

Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current model editors, which modify such behaviors of pre-trained models, degrade model performance quickly across multiple, sequential edits. We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs. GRACE writes new mappings into a pre-trained model's latent space, creating a discrete, local codebook of edits without altering model weights. This is the first method enabling thousands of sequential edits using only streaming errors. Our experiments on T5, BERT, and GPT models show GRACE's state-of-the-art performance in making and retaining edits, while generalizing to unseen inputs. Our code is available at https://www.github.com/thartvigsen/grace}.

Key facts. Cited by 267 papers in the map (data through 7 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 20 Nov 2022.

Builds on

36 of 49 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2017Neural Discrete Representation Learningcited by 4,650
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  8. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  9. 2018Experience Replay for Continual Learningcited by 1,074
  10. 2022Mass-Editing Memory in a Transformercited by 976
  11. 2021Learning to Prompt for Continual Learningcited by 938
  12. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
24 more
  1. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  2. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  3. 2021Editing Factual Knowledge in Language Modelscited by 548
  4. 2021Fast Model Editing at Scalecited by 491
  5. 2022Memory-Based Model Editing at Scalecited by 443
  6. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  7. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  8. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
  9. 2014Memory Networkscited by 354
  10. 2021Post-Training Quantization for Vision Transformercited by 274
  11. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 226
  12. 2020Modifying Memories in Transformer Modelscited by 222
  13. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  14. 2020Editable Neural Networkscited by 154
  15. 2019Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Modelscited by 141
  16. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  17. 2021On Transferability of Prompt Tuning for Natural Language Processingcited by 74
  18. 2022FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processingcited by 48
  19. 2022Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infillingcited by 38
  20. 2022PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptationcited by 31
  21. 2022Language Anisotropic Cross-Lingual Model Editingcited by 26
  22. 2022On Continual Model Refinement in Out-of-Distribution Data Streamscited by 22
  23. 2022Discrete Key-Value Bottleneckcited by 18
  24. 2021A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imagingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 18; 2024: 85; 2025: 90; 2026: 74.

267 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  3. 2023Challenges and Applications of Large Language Modelscited by 251
  4. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  5. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  6. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  7. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  8. 2024Continual Learning with Pre-Trained Models: A Surveycited by 151
  9. 2025MemOS: A Memory OS for AI Systemcited by 129
  10. 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 97
  11. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  12. 2024Detoxifying Large Language Models via Knowledge Editingcited by 86
38 more
  1. 2024BadEdit: Backdooring large language models by model editingcited by 84
  2. 2023MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRAcited by 80
  3. 2025AnyEdit: Edit Any Knowledge Encoded in Language Modelscited by 74
  4. 2024MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learningcited by 63
  5. 2024MyVLM: Personalizing VLMs for User-Specific Queriescited by 58
  6. 2024Larimar: Large Language Models with Episodic Memory Controlcited by 53
  7. 2024A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicinecited by 45
  8. 2023Can We Edit Multimodal Large Language Models?cited by 44
  9. 2024Learning to Edit: Aligning LLMs with Knowledge Editingcited by 43
  10. 2024WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editingcited by 40
  11. 2024Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learningcited by 40
  12. 2024Multi-hop Question Answering under Temporal Knowledge Editingcited by 36
  13. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  14. 2024AKEW: Assessing Knowledge Editing in the Wildcited by 35
  15. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  16. 2024MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memorycited by 35
  17. 2023Evaluating the Reversal Curse in Model Editingcited by 34
  18. 2023A Survey on Knowledge Editing of Neural Networkscited by 34
  19. 2023How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advancescited by 33
  20. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 33
  21. 2025Reinforced Lifelong Editing for Language Modelscited by 33
  22. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmarkcited by 30
  23. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  24. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  25. 2024Perturbation-Restrained Sequential Model Editingcited by 27
  26. 2023DocTER: Evaluating Document-based Knowledge Editingcited by 26
  27. 2025WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMscited by 25
  28. 2024Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?cited by 24
  29. 2025The Mirage of Model Editing: Revisiting Evaluation in the Wildcited by 24
  30. 2023Overcoming Generic Knowledge Loss with Selective Parameter Updatecited by 23
  31. 2023Editing Personality for Large Language Modelscited by 22
  32. 2024Model Editing by Standard Fine-Tuningcited by 22
  33. 2025MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledgecited by 22
  34. 2024Editing Conceptual Knowledge for Large Language Modelscited by 21
  35. 2024Ethos: Rectifying Language Models in Orthogonal Parameter Spacecited by 20
  36. 2024RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuningcited by 20
  37. 2024InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integrationcited by 19
  38. 2024Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Modelscited by 18

50 most cited of 267 All 267 (JSON)