LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing

• URL: http://arxiv.org/abs/2505.15702v1
• Date: Wed, 21 May 2025 16:16:33 GMT
• Title: LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
• Authors: Peng Wang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu,
• Abstract summary: Current locate-then-edit approaches exhibit a progressive performance decline during sequential editing.<n>textbfLyapLock is proposed to decompose the long-term constrained programming into tractable stepwise subproblems for efficient solving.<n> Experimental results show that our framework scales sequential editing capacity to over 10,000 edits while stabilizing general capabilities and boosting average editing efficacy by 11.89% over SOTA baselines.
• Score: 27.918524905286475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models often contain factually incorrect or outdated knowledge, giving rise to model editing methods for precise knowledge updates. However, current mainstream locate-then-edit approaches exhibit a progressive performance decline during sequential editing, due to inadequate mechanisms for long-term knowledge preservation. To tackle this, we model the sequential editing as a constrained stochastic programming. Given the challenges posed by the cumulative preservation error constraint and the gradually revealed editing tasks, \textbf{LyapLock} is proposed. It integrates queuing theory and Lyapunov optimization to decompose the long-term constrained programming into tractable stepwise subproblems for efficient solving. This is the first model editing framework with rigorous theoretical guarantees, achieving asymptotic optimal editing performance while meeting the constraints of long-term knowledge preservation. Experimental results show that our framework scales sequential editing capacity to over 10,000 edits while stabilizing general capabilities and boosting average editing efficacy by 11.89\% over SOTA baselines. Furthermore, it can be leveraged to enhance the performance of baseline methods. Our code is released on https://github.com/caskcsg/LyapLock.

Related papers

• MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs [82.34547399693966]
  Existing methods for lifelong model editing compromise generalization, interfere with past edits, or fail to scale to long editing sequences.<n>We propose MEMOIR, a novel scalable framework that injects knowledge through a residual memory.<n>MeMOIR confines each edit to a distinct subset of the memory parameters, minimizing interference among edits.
  arXiv  Detail & Related papers  (2025-06-09T16:16:42Z)
• UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models [18.23723680134397]
  Lifelong learning enables large language models to adapt to evolving information by continually updating their internal knowledge.<n>Model editing stands out as a promising solution for this goal, offering a focused and efficient way to revise a model's internal knowledge.<n>UltraEdit is training-, subject- and memory-free, making it well-suited for ultra-scalable, real-world lifelong model editing.
  arXiv  Detail & Related papers  (2025-05-20T17:59:04Z)
• DeltaEdit: Enhancing Sequential Editing in Large Language Models by Controlling Superimposed Noise [1.2697731449512988]
  Sequential knowledge editing techniques aim to continuously update the knowledge in large language models at a low cost.<n>Existing sequential editing methods suffer from a significant decline in editing success rates after long-term editing.<n>We propose DeltaEdit, a novel method that reduces interference between edits to mitigate deviation.<n> Experimental results demonstrate that DeltaEdit significantly outperforms existing methods in edit success rates and the retention of generalization capabilities.
  arXiv  Detail & Related papers  (2025-05-12T07:11:26Z)
• The Mirage of Model Editing: Revisiting Evaluation in the Wild [70.17413507444704]
  We introduce QAEdit, a new benchmark aligned with widely used question answering (QA) datasets, and WILD, a task-agnostic evaluation framework.<n>Our single editing experiments show that current editing methods perform substantially worse than previously reported.
  arXiv  Detail & Related papers  (2025-02-16T15:57:55Z)
• Lifelong Knowledge Editing requires Better Regularization [11.14177136208272]
  We formalize the popular locate-then-edit methods as a two-step fine-tuning process.<n>We show that model degradation occurs due to over-optimization of internal activations and continuous norm-growth of edited matrices.<n>Applying these simple yet effective regularization techniques at key points in the editing process can substantially mitigate model degradation.
  arXiv  Detail & Related papers  (2025-02-03T18:59:14Z)
• O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing [0.0]
  Large language models (LLMs) acquire knowledge during pre-training, but over time, this knowledge may become incorrect or outdated, necessitating updates after training. We propose Orthogonal Subspace Editing, O-Edit. This algorithmizes the direction of each knowledge update, minimizing interference between successive updates and reducing the impact of new updates on unrelated knowledge. It can perform thousands of edits on mainstream LLMs, achieving an average performance improvement that is 4.2 times better than existing methods while effectively preserving the model's performance on downstream tasks, all with minimal additional parameter overhead.
  arXiv  Detail & Related papers  (2024-10-15T10:16:45Z)
• ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA [55.697627106315004]
  Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors.<n>Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update.<n>We propose ELDER, a novel approach to create a continuous association between data and adapters.
  arXiv  Detail & Related papers  (2024-08-19T02:27:00Z)
• Perturbation-Restrained Sequential Model Editing [33.51709226068619]
  Current model editing methods compromise the general abilities of large language models (LLMs) as the number of edits increases.<n>A framework termed Perturbation Restraint on Upper bouNd for Editing (PRUNE) is proposed, which applies the condition number restraints in sequential editing.<n>The results show that PRUNE can preserve general abilities while maintaining the editing performance effectively in sequential model editing.
  arXiv  Detail & Related papers  (2024-05-27T04:40:56Z)
• Consecutive Batch Model Editing with HooK Layers [59.673084839708224]
  CoachHooK is a model editing method that simultaneously supports sequential and batch editing. It is memory-friendly as it only needs a small amount of it to store several hook layers whose size remains unchanged over time.
  arXiv  Detail & Related papers  (2024-03-08T14:07:44Z)
• The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse [58.0132400208411]
  Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks. benchmarking Large Language Models after each edit is impractically time-consuming and resource-intensive. We have utilized GPT-3.5 to develop a new dataset, HardEdit, based on hard cases.
  arXiv  Detail & Related papers  (2024-02-15T01:50:38Z)
• Memory-Based Model Editing at Scale [102.28475739907498]
  Existing model editors struggle to accurately model an edit's intended scope. We propose Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model (SERAC) SERAC stores edits in an explicit memory and learns to reason over them to modulate the base model's predictions as needed.
  arXiv  Detail & Related papers  (2022-06-13T23:40:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.