mlsanityData to 7 Oct 2026

Transformer-Patcher: One Mistake worth One Neuron

arXiv 2301.09785 ↗First posted 24 Jan 2023cs.CL cs.AIcited by 196

Not on the map. Why?

Abstract (arXiv)

Large Transformer-based Pretrained Language Models (PLMs) dominate almost all Natural Language Processing (NLP) tasks. Nevertheless, they still make mistakes from time to time. For a model deployed in an industrial environment, fixing these mistakes quickly and robustly is vital to improve user experiences. Previous works formalize such problems as Model Editing (ME) and mostly focus on fixing one mistake. However, the one-mistake-fixing scenario is not an accurate abstraction of the real-world challenge. In the deployment of AI services, there are ever-emerging mistakes, and the same mistake may recur if not corrected in time. Thus a preferable solution is to rectify the mistakes as soon as they appear nonstop. Therefore, we extend the existing ME into Sequential Model Editing (SME) to help develop more practical editing methods. Our study shows that most current ME methods could yield unsatisfying results in this scenario. We then introduce Transformer-Patcher, a novel model editor that can shift the behavior of transformer-based models by simply adding and training a few neurons in the last Feed-Forward Network layer. Experimental results on both classification and generation tasks show that Transformer-Patcher can successively correct up to thousands of errors (Reliability) and generalize to their equivalent inputs (Generality) while retaining the model's accuracy on irrelevant inputs (Locality). Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME). The code is available at https://github.com/ZeroYuHuang/Transformer-Patcher.

Key facts. Cited by 196 papers in the map (data through 7 Oct 2026). Builds on 26 of its 33 references that are in the map. First posted on arXiv 24 Jan 2023.

Builds on

26 of 33 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2016Learning without Forgettingcited by 2,465
  8. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  9. 2016Progressive Neural Networkscited by 1,332
  10. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  11. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  12. 2021Knowledge Neurons in Pretrained Transformerscited by 590
14 more
  1. 2021Editing Factual Knowledge in Language Modelscited by 548
  2. 2021Fast Model Editing at Scalecited by 491
  3. 2022Memory-Based Model Editing at Scalecited by 443
  4. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  5. 2020Supermasks in Superpositioncited by 223
  6. 2020Modifying Memories in Transformer Modelscited by 222
  7. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  8. 2019Episodic Memory in Lifelong Language Learningcited by 188
  9. 2020Editable Neural Networkscited by 154
  10. 2019Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systemscited by 110
  11. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 86
  12. 2021Provable Repair of Deep Neural Networkscited by 39
  13. 2022LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Modelscited by 28
  14. 2020Towards Interpreting BERT for Reading Comprehension Based QAcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 26; 2024: 97; 2025: 46; 2026: 27.

196 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  3. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  4. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 292
  5. 2025Memory in the Age of AI Agentscited by 285
  6. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  7. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  8. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  9. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  10. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  11. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  12. 2023Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Eraserscited by 118
38 more
  1. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 101
  2. 2023EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Modelscited by 97
  3. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  4. 2024Detoxifying Large Language Models via Knowledge Editingcited by 86
  5. 2024BadEdit: Backdooring large language models by model editingcited by 84
  6. 2023MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRAcited by 80
  7. 2025AnyEdit: Edit Any Knowledge Encoded in Language Modelscited by 74
  8. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  9. 2023Massive Editing for Large Language Models via Meta Learningcited by 62
  10. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  11. 2024Larimar: Large Language Models with Episodic Memory Controlcited by 53
  12. 2024From Understanding to Utilization: A Survey on Explainability for Large Language Modelscited by 47
  13. 2024A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicinecited by 45
  14. 2023Can We Edit Multimodal Large Language Models?cited by 44
  15. 2024WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editingcited by 40
  16. 2024Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learningcited by 40
  17. 2024Uncovering Overfitting in Large Language Model Editingcited by 36
  18. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  19. 2024MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memorycited by 35
  20. 2023Evaluating the Reversal Curse in Model Editingcited by 34
  21. 2023A Survey on Knowledge Editing of Neural Networkscited by 34
  22. 2023How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advancescited by 33
  23. 2024DeepEdit: Knowledge Editing as Decoding with Constraintscited by 33
  24. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 33
  25. 2025Reinforced Lifelong Editing for Language Modelscited by 33
  26. 2023Identifying and Mitigating Privacy Risks Stemming from Language Models: A Surveycited by 30
  27. 2024VLKEB: A Large Vision-Language Model Knowledge Editing Benchmarkcited by 30
  28. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  29. 2023DocTER: Evaluating Document-based Knowledge Editingcited by 26
  30. 2025The Mirage of Model Editing: Revisiting Evaluation in the Wildcited by 24
  31. 2024Long-form evaluation of model editingcited by 23
  32. 2024Configurable Foundation Models: Building LLMs from a Modular Perspectivecited by 22
  33. 2023Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Modelscited by 21
  34. 2024Editing Conceptual Knowledge for Large Language Modelscited by 21
  35. 2024Self-Updatable Large Language Models by Integrating Context into Model Parameterscited by 21
  36. 2024Ethos: Rectifying Language Models in Orthogonal Parameter Spacecited by 20
  37. 2024RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuningcited by 20
  38. 2024InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integrationcited by 19

50 most cited of 196 All 196 (JSON)