Decomposing Task Vectors for Refined Model Editing

• URL: http://arxiv.org/abs/2512.22511v1
• Date: Sat, 27 Dec 2025 07:53:44 GMT
• Title: Decomposing Task Vectors for Refined Model Editing
• Authors: Hamed Damirchi, Ehsan Abbasnejad, Zhen Zhang, Javen Shi,
• Abstract summary: We propose a principled decomposition method that separates each task vector into two components.<n>By identifying invariant subspaces across projections, our approach enables more precise control over concept manipulation.
• Score: 21.799465464971092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large pre-trained models have transformed machine learning, yet adapting these models effectively to exhibit precise, concept-specific behaviors remains a significant challenge. Task vectors, defined as the difference between fine-tuned and pre-trained model parameters, provide a mechanism for steering neural networks toward desired behaviors. This has given rise to large repositories dedicated to task vectors tailored for specific behaviors. The arithmetic operation of these task vectors allows for the seamless combination of desired behaviors without the need for large datasets. However, these vectors often contain overlapping concepts that can interfere with each other during arithmetic operations, leading to unpredictable outcomes. We propose a principled decomposition method that separates each task vector into two components: one capturing shared knowledge across multiple task vectors, and another isolating information unique to each specific task. By identifying invariant subspaces across projections, our approach enables more precise control over concept manipulation without unintended amplification or diminution of other behaviors. We demonstrate the effectiveness of our decomposition method across three domains: improving multi-task merging in image classification by 5% using shared components as additional task vectors, enabling clean style mixing in diffusion models without generation degradation by mixing only the unique components, and achieving 47% toxicity reduction in language models while preserving performance on general knowledge tasks by negating the toxic information isolated to the unique component. Our approach provides a new framework for understanding and controlling task vector arithmetic, addressing fundamental limitations in model editing operations.

Related papers

• Escaping Optimization Stagnation: Taking Steps Beyond Task Arithmetic via Difference Vectors [7.805099851866648]
  Current methods for editing pre-trained models face significant challenges, primarily high computational costs and limited scalability.<n> Task arithmetic has recently emerged as a promising solution, using simple arithmetic operations-addition and negation-based on task vectors.<n>We propose Difference Vector-based Anisotropic Scaling Iterative algorithm (DV-BASI) to enable a continuous optimization process for task arithmetic methods.
  arXiv  Detail & Related papers  (2025-11-22T09:01:05Z)
• Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging [83.5273168208788]
  Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training.<n>The merged model often suffers from notable performance degradation due to the conflicts caused by task-irrelevant redundancy in task vectors.<n>We propose Purifying TAsk Vectors (PAVE) in knowledge-aware subspace to overcome these challenges.
  arXiv  Detail & Related papers  (2025-10-16T14:02:57Z)
• Variational Task Vector Composition [53.476598858325985]
  We propose variational task vector composition, where composition coefficients are taken as latent variables and estimated in a Bayesian inference framework.<n>Motivated by the observation of structural redundancy in task vectors, we introduce a Spike-and-Slab prior that promotes sparsity.<n>We develop a gated sampling mechanism that constructs a controllable posterior by filtering the composition coefficients based on both uncertainty and importance.
  arXiv  Detail & Related papers  (2025-09-21T02:46:02Z)
• When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers [64.1656365676171]
  Task arithmetic refers to editing the pre-trained model by adding a weighted sum of task vectors.<n>This paper theoretically prove the effectiveness of task addition in simultaneously learning a set of irrelevant or irrelevant tasks.<n>We prove the proper selection for task arithmetic to achieve negation to out-of-domain tasks.
  arXiv  Detail & Related papers  (2025-04-15T08:04:39Z)
• Multi-Task Model Merging via Adaptive Weight Disentanglement [69.7292615212444]
  We introduce an Adaptive Weight Disentanglement method for model merging.<n>We successfully extract redundant vectors, and after their subtraction, the task vectors retain robust performance.
  arXiv  Detail & Related papers  (2024-11-27T20:08:55Z)
• Knowledge Composition using Task Vectors with Learned Anisotropic Scaling [51.4661186662329]
  We introduce aTLAS, an algorithm that linearly combines parameter blocks with different learned coefficients, resulting in anisotropic scaling at the task vector level. We show that such linear combinations explicitly exploit the low intrinsicity of pre-trained models, with only a few coefficients being the learnable parameters. We demonstrate the effectiveness of our method in task arithmetic, few-shot recognition and test-time adaptation, with supervised or unsupervised objectives.
  arXiv  Detail & Related papers  (2024-07-03T07:54:08Z)
• Editing Models with Task Arithmetic [69.97273155842966]
  Changing how pre-trained models behave is a common practice when developing machine learning systems. We build task vectors by subtracting the weights of a pre-trained model from the weights of the same model after fine-tuning on a task. We show that these task vectors can be modified and combined together through arithmetic operations such as negation and addition.
  arXiv  Detail & Related papers  (2022-12-08T05:50:53Z)

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.