mlsanityData to 7 Oct 2026

CoME: An Unlearning-based Approach to Conflict-free Model Editing

arXiv 2502.15826 ↗First posted 20 Feb 2025cs.CL cs.AIcited by 12

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. While model editing methods have been developed to address such errors without full re-training, they frequently suffer from knowledge conflicts, where outdated information interferes with new knowledge. In this work, we propose Conflict-free Model Editing (CoME), a novel framework that enhances the accuracy of knowledge updates in LLMs by selectively removing outdated knowledge. CoME leverages unlearning to mitigate knowledge interference, allowing new information to be integrated without compromising relevant linguistic features. Through experiments on GPT-J and LLaMA-3 using Counterfact and ZsRE datasets, we demonstrate that CoME improves both editing accuracy and model reliability when applied to existing editing methods. Our results highlight that the targeted removal of outdated knowledge is crucial for enhancing model editing effectiveness and maintaining the model's generative performance.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 27 of its 44 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

27 of 44 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMs31 Oct
  2. 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct
  3. 2023Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation16 Aug
  4. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct

Other references · 23

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2022Mass-Editing Memory in a Transformercited by 976
  3. 2021Editing Factual Knowledge in Language Modelscited by 548
  4. 2022Memory-Based Model Editing at Scalecited by 443
  5. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  6. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  7. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 285
  8. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 284
  9. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
  10. 2020Modifying Memories in Transformer Modelscited by 222
  11. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  12. 2023PMET: Precise Model Editing in a Transformercited by 170
11 more
  1. 2020Editable Neural Networkscited by 154
  2. 2023Inspecting and Editing Knowledge Representations in Language Modelscited by 140
  3. 2020Self-Attention Attribution: Interpreting Information Interactions Inside Transformercited by 124
  4. 2021Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Basescited by 107
  5. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 101
  6. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  7. 2022Understanding Transformer Memorization Recall Through Idiomscited by 62
  8. 2024WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editingcited by 40
  9. 2024Locating and Editing Factual Associations in Mambacited by 35
  10. 2023Emptying the Ocean with a Spoon: Should We Edit Models?cited by 27
  11. 2024Large Language Model Bias Mitigation from the Perspective of Knowledge Editingcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 6.

12 papers.

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  2. 2025Model Unlearning via Sparse Autoencoder Subspace Guided Projectionscited by 17
  3. 2026Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearningcited by 5
  4. 2025Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocolscited by 4
  5. 2025KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearningcited by 3
  6. 2026Position: The Term "Machine Unlearning" Is Overused in LLMscited by 3
  7. 2025A Survey on Unlearning in Large Language Modelscited by 2
  8. 2025Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Modelscited by 0
  9. 2026Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updatescited by 0
  10. 2026HARP: Hierarchical Adaptive Ranking with Preference-Adaptive Fusion for Query-Based CVE Prioritizationcited by 0
  11. 2026The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearningcited by 0
  12. 2026SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearningcited by 0