mlsanityData to 7 Oct 2026

Generalizable Lifelong Model Editing via Preference Optimization

arXiv 2609.36748 ↗First posted 29 Sep 2026cs.AIcited by 0

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

Knowledge editing enables rapid updates of specific factual knowledge in large language models (LLMs) without full retraining. However, more realistic scenarios call for a lifelong framework that handles continual updates rather than one-off modifications. In such settings, existing editing methods often overfit to target prompts, significantly degrading both the generalization of the edited knowledge and the model's general capabilities. To address this issue, we propose GLIME (Generalizable Lifelong Model Editing), which combines knowledge editing with preference optimization over generation behavior. GLIME further incorporates replay-based editing and a gradient constraint to preserve previously edited knowledge. Experimental results show that GLIME significantly improves knowledge generalization in lifelong editing settings while maintaining both editing performance and general capabilities.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 30 of its 41 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

30 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024ORPO: Monolithic Preference Optimization without Reference Model12 Mar

Other references · 29

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  5. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  6. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  7. 2024A Survey on LLM-as-a-Judgecited by 1,384
  8. 2018Experience Replay for Continual Learningcited by 1,074
  9. 2022Mass-Editing Memory in a Transformercited by 976
  10. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  11. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  12. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
17 more
  1. 2021Editing Factual Knowledge in Language Modelscited by 548
  2. 2022Memory-Based Model Editing at Scalecited by 443
  3. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  4. 2019Orthogonal Gradient Descent for Continual Learningcited by 361
  5. 2021Gradient Projection Memory for Continual Learningcited by 338
  6. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 292
  7. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
  8. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 228
  9. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  10. 2020Modifying Memories in Transformer Modelscited by 222
  11. 2024Model Editing at Scale leads to Gradual and Catastrophic Forgettingcited by 92
  12. 2024ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMcited by 73
  13. 2022Understanding Transformer Memorization Recall Through Idiomscited by 62
  14. 2024Rebuilding ROME : Resolving Model Collapse during Sequential Model Editingcited by 50
  15. 2025WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMscited by 25
  16. 2025The Mirage of Model Editing: Revisiting Evaluation in the Wildcited by 24
  17. 2025Continual Gradient Low-Rank Projection Fine-Tuning for LLMscited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning
  2. 2024WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
  3. 2026More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
  4. 2026Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models
  5. 2023Knowledge Editing for Large Language Models: A Survey
  6. 2024LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models
  7. 2026The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
  8. 2025Benchmarking and Rethinking Knowledge Editing for Large Language Models