# Decomposing Task Vectors for Refined Model Editing

arXiv: https://arxiv.org/abs/2512.22511 · HTML: https://mlsanity.com/paper/2512.22511/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Dataless Knowledge Fusion by Merging Weights of Language Models](https://mlsanity.com/paper/2212.09849/) (2022)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [AdaMerging: Adaptive Model Merging for Multi-Task Learning](https://mlsanity.com/paper/2310.02575/) (2023)
- [Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models](https://mlsanity.com/paper/2305.12827/) (2023)
- [MNIST-C: A Robustness Benchmark for Computer Vision](https://mlsanity.com/paper/1906.02337/) (2019)
- [Knowledge Composition using Task Vectors with Learned Anisotropic Scaling](https://mlsanity.com/paper/2407.02880/) (2024)
- [Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing](https://mlsanity.com/paper/2407.08770/) (2024)

## Built on by (most cited first, 1 of 1)

- [Training-Free Task Vectors for LLM Behavioral Control](https://mlsanity.com/paper/2609.09054/) (2026)

## Abstract (arXiv)

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.