mlsanityData to 7 Oct 2026

Editable Neural Networks

arXiv 2004.00345 ↗First posted 1 Apr 2020cs.LG stat.MLcited by 154

Not on the map. Why?

Abstract (arXiv)

These days deep neural networks are ubiquitously used in a wide range of tasks, from image classification and machine translation to face identification and self-driving cars. In many applications, a single model error can lead to devastating financial, reputational and even life-threatening consequences. Therefore, it is crucially important to correct model mistakes quickly as they appear. In this work, we investigate the problem of neural network editing - how one can efficiently patch a mistake of the model on a particular sample, without influencing the model behavior on other samples. Namely, we propose Editable Training, a model-agnostic training technique that encourages fast editing of the trained model. We empirically demonstrate the effectiveness of this method on large-scale image classification and machine translation tasks.

Key facts. Cited by 154 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 19; 2023: 43; 2024: 47; 2025: 24; 2026: 14.

154 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2022Mass-Editing Memory in a Transformercited by 976
  3. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  4. 2021Editing Factual Knowledge in Language Modelscited by 548
  5. 2021Fast Model Editing at Scalecited by 491
  6. 2022Memory-Based Model Editing at Scalecited by 443
  7. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  8. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 292
  9. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 290
  10. 2022Post-hoc Concept Bottleneck Modelscited by 289
  11. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  12. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
38 more
  1. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  2. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  3. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 226
  4. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 196
  5. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  6. 2022Patching open-vocabulary models by interpolating weightscited by 187
  7. 2023PMET: Precise Model Editing in a Transformercited by 170
  8. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  9. 2023Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Eraserscited by 118
  10. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 101
  11. 2023Deep Model Fusion: A Surveycited by 89
  12. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  13. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  14. 2023Permutation Equivariant Neural Functionalscited by 69
  15. 2023Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledgecited by 66
  16. 2023Can Neural Network Memorization Be Localized?cited by 66
  17. 2023Massive Editing for Large Language Models via Meta Learningcited by 62
  18. 2024MyVLM: Personalizing VLMs for User-Specific Queriescited by 58
  19. 2022Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Modelscited by 56
  20. 2022Entity Cloze By Date: What LMs Know About Unseen Entitiescited by 55
  21. 2022Mechanistic Mode Connectivitycited by 50
  22. 2023Can We Edit Multimodal Large Language Models?cited by 44
  23. 2023Meta-Learning Online Adaptation of Language Modelscited by 43
  24. 2024Learning to Edit: Aligning LLMs with Knowledge Editingcited by 43
  25. 2022Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inferencecited by 40
  26. 2021Provable Repair of Deep Neural Networkscited by 39
  27. 2024Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Factscited by 36
  28. 2024AKEW: Assessing Knowledge Editing in the Wildcited by 35
  29. 2024MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memorycited by 35
  30. 2023Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memoriescited by 34
  31. 2023Evaluating the Reversal Curse in Model Editingcited by 34
  32. 2023A Survey on Knowledge Editing of Neural Networkscited by 34
  33. 2023Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operationcited by 33
  34. 2023How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advancescited by 33
  35. 2024In-Context Editing: Learning Knowledge from Self-Induced Distributionscited by 33
  36. 2023Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarkscited by 29
  37. 2023Editing Common Sense in Transformerscited by 28
  38. 2023Propagating Knowledge Updates to LMs Through Distillationcited by 28

50 most cited of 154 All 154 (JSON)