Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse

• URL: http://arxiv.org/abs/2601.11042v1
• Date: Fri, 16 Jan 2026 07:18:14 GMT
• Title: Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
• Authors: Chi Zhang, Mengqi Zhang, Xiaotian Ye, Runxi Cheng, Zisheng Zhou, Ying Zhou, Pengjie Ren, Zhumin Chen,
• Abstract summary: We show that a model's general abilities are closely associated with dominant singular directions of pretrained weight matrices.<n>We propose REVIVE, a plug-and-play framework that stabilizes sequential editing by explicitly preserving the dominant singular subspace.
• Score: 44.49646322759214
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on parameter updates, yet the mechanisms underlying such degradation remain insufficiently understood. In this work, we present a spectral analysis of sequential knowledge editing and show that a model's general abilities are closely associated with dominant singular directions of pretrained weight matrices. These directions are highly sensitive to perturbations and are progressively disrupted by repeated edits, closely tracking the collapse in both editing efficacy and general performance. Building on this insight, we propose REVIVE, a plug-and-play framework that stabilizes sequential editing by explicitly preserving the dominant singular subspace. REVIVE represents parameter updates in the spectral basis of the original weights and filters components that would interfere with the protected region. Extensive experiments across multiple models and benchmarks show that REVIVE consistently improves editing efficacy while substantially preserving general abilities under long-horizon sequential editing, including extreme settings with up to 20,000 edits.

Related papers

• ConsistEdit: Highly Consistent and Precise Training-free Visual Editing [17.162316662697965]
  We propose ConsistEdit, a novel attention control method specifically tailored for MM-DiT.<n>It incorporates vision-only attention control, mask-guided pre-attention fusion, and differentiated manipulation of the query, key, and value tokens.<n>It achieves state-of-the-art performance across a wide range of image and video editing tasks, including both structure-consistent and structure-inconsistent scenarios.
  arXiv  Detail & Related papers  (2025-10-20T17:59:52Z)
• EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing [19.834477925624658]
  Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge.<n>Existing approaches are mainly based on a locate-then-edit framework.<n>We introduce EvoEdit, a novel editing strategy that mitigates catastrophic interference through sequential null-space alignment.
  arXiv  Detail & Related papers  (2025-10-11T21:36:14Z)
• Energy-Regularized Sequential Model Editing on Hyperspheres [59.47007547581175]
  Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge.<n> sequential editing often destabilizes representations and induces catastrophic forgetting.<n>We propose SPHERE (Sparse Projection for Hyperspherical Energy-Regularized Editing), an HE-driven regularization strategy that stabilizes neuron weight distributions.
  arXiv  Detail & Related papers  (2025-10-01T17:55:43Z)
• MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs [76.28901550926021]
  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, while preserving the core capabilities of the pre-trained model.<n>MeMOIR achieves state-of-the-art performance across reliability, generalization, and locality metrics, scaling to thousands of sequential edits with minimal forgetting.
  arXiv  Detail & Related papers  (2025-06-09T16:16:42Z)
• Weight Spectra Induced Efficient Model Adaptation [54.8615621415845]
  Fine-tuning large-scale foundation models incurs prohibitive computational costs.<n>We show that fine-tuning predominantly amplifies the top singular values while leaving the remainder largely intact.<n>We propose a novel method that leverages learnable rescaling of top singular directions.
  arXiv  Detail & Related papers  (2025-05-29T05:03:29Z)
• LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing [28.870053452479443]
  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.
  arXiv  Detail & Related papers  (2025-05-21T16:16:33Z)
• Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing [60.730661748555214]
  We introduce textbfTask-textbfOriented textbfDiffusion textbfInversion (textbfTODInv), a novel framework that inverts and edits real images tailored to specific editing tasks. ToDInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability.
  arXiv  Detail & Related papers  (2024-08-23T22:16:34Z)
• 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)
• Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue [122.20016030723043]
  We evaluate the side effects of model editing on large language models (LLMs) Our analysis reveals that the side effects are caused by model editing altering the original model weights excessively. To mitigate this, a method named RECT is proposed to regularize the edit update weights.
  arXiv  Detail & Related papers  (2024-01-09T18:03:15Z)

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.