mlsanityData to 14 Oct 2026

AnyEdit: Edit Any Knowledge Encoded in Language Models

arXiv 2502.05628 ↗First posted 8 Feb 2025cs.CLcited by 76

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) often produce incorrect or outdated information, necessitating efficient and precise knowledge updates. Current model editing methods, however, struggle with long-form knowledge in diverse formats, such as poetry, code snippets, and mathematical derivations. These limitations arise from their reliance on editing a single token's hidden state, a limitation we term "efficacy barrier". To solve this, we propose AnyEdit, a new autoregressive editing paradigm. It decomposes long-form knowledge into sequential chunks and iteratively edits the key token in each chunk, ensuring consistent and accurate outputs. Theoretically, we ground AnyEdit in the Chain Rule of Mutual Information, showing its ability to update any knowledge within LLMs. Empirically, it outperforms strong baselines by 21.5% on benchmarks including UnKEBench, AKEW, and our new EditEverything dataset for long-form diverse-formatted knowledge. Additionally, AnyEdit serves as a plug-and-play framework, enabling current editing methods to update knowledge with arbitrary length and format, significantly advancing the scope and practicality of LLM knowledge editing.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 8 Feb 2025.

Builds on

27 of 38 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  7. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  8. 2022Mass-Editing Memory in a Transformercited by 1,001
  9. 2021Editing Factual Knowledge in Language Modelscited by 553
  10. 2021Fast Model Editing at Scalecited by 498
  11. 2022Memory-Based Model Editing at Scalecited by 447
  12. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 285
15 more
  1. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 271
  2. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 236
  3. 2020Modifying Memories in Transformer Modelscited by 224
  4. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 197
  5. 2024Orca-Math: Unlocking the potential of SLMs in Grade School Mathcited by 151
  6. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 103
  7. 2024FlipAttack: Jailbreak LLMs via Flippingcited by 80
  8. 2024AKEW: Assessing Knowledge Editing in the Wildcited by 36
  9. 2024Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Factscited by 36
  10. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  11. 2024Can Editing LLMs Inject Harm?cited by 22
  12. 2024Neuron-Level Sequential Editing for Large Language Modelscited by 20
  13. 2024Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Modelscited by 19
  14. 2024Commonsense Knowledge Editing Based on Free-Text in LLMscited by 16
  15. 2024Structure Guided Large Language Model for SQL Generationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 36; 2026: 40.

76 papers.

Sort:

By area:

  1. 2025MemOS: A Memory OS for AI Systemcited by 138
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  3. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  4. 2025OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editingcited by 53
  5. 2025OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generationcited by 50
  6. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 49
  7. 2025When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generationcited by 48
  8. 2025Reinforced Lifelong Editing for Language Modelscited by 34
  9. 2025FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generationcited by 28
  10. 2025EditThinker: Unlocking Iterative Reasoning for Any Image Editorcited by 25
  11. 2025Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atomscited by 24
  12. 2025BiasEdit: Debiasing Stereotyped Language Models via Model Editingcited by 18
38 more
  1. 2025Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generationcited by 17
  2. 2025Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?cited by 13
  3. 2025OmniTry: Virtual Try-On Anything without Maskscited by 13
  4. 2025CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learnerscited by 9
  5. 2025UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Modelscited by 9
  6. 2026Why Steering Works: Toward a Unified View of Language Model Parameter Dynamicscited by 9
  7. 2025When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorationscited by 7
  8. 2026Fine-Grained Activation Steering: Steering Less, Achieving Morecited by 7
  9. 2025ACE: Concept Editing in Diffusion Models without Performance Degradationcited by 6
  10. 2025Is Fine-Tuning an Effective Solution? Reassessing Knowledge Editing for Unstructured Datacited by 6
  11. 2025μKE: Matryoshka Unstructured Knowledge Editing of Large Language Modelscited by 5
  12. 2025SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Modelscited by 5
  13. 2026Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapsecited by 5
  14. 2026MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledgecited by 5
  15. 2025Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editingcited by 4
  16. 2025POME: Post Optimization Model Edit via Muon-style Projectioncited by 4
  17. 2026Are We Evaluating the Edit Locality of LLM Model Editing Properly?cited by 4
  18. 2026Uncovering Context Reliance in Unstructured Knowledge Editingcited by 4
  19. 2025Representation Interventions Enable Lifelong Knowledge Memory Control in LLMscited by 3
  20. 2025VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesiscited by 3
  21. 2026Mitigating Hallucinations in Large Vision-Language Models without Performance Degradationcited by 3
  22. 2026Steering Visual Generation in Unified Multimodal Models with Understanding Supervisioncited by 3
  23. 2026CoT-Edit: Let CoT Guide Instruction Video Editingcited by 3
  24. 2025ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Mergingcited by 2
  25. 2025On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language Modelscited by 2
  26. 2025EditMF: Drawing an Invisible Fingerprint for Your Large Language Modelscited by 2
  27. 2025Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMscited by 2
  28. 2025EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusioncited by 2
  29. 2026Mitigating Memorization Where It Happenscited by 2
  30. 2026Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Modelscited by 2
  31. 2026FABLE: Fine-grained Fact Anchoring for Unstructured Model Editingcited by 2
  32. 2026From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editingcited by 2
  33. 2026AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprisecited by 2
  34. 2025PD3F: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Modelscited by 1
  35. 2025DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal Regulationcited by 1
  36. 2025bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMscited by 1
  37. 2025EtCon: Edit-then-Consolidate for Reliable Knowledge Editingcited by 1
  38. 2026Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editingcited by 1

50 most cited of 76 All 76 (JSON)