Beyond Uniform SVD: Dual-Level Optimization across Columns and Modules for LLM Compression

ACL ARR 2026 January Submission3776 Authors

Keywords: LLM Compression, Singular Value Decomposition, Structural Heterogeneity, Dual-Level Optimization

Abstract: Low-rank decomposition, particularly Singular Value Decomposition (SVD), is a pivotal technique for mitigating the storage and computational demands of Large Language Models (LLMs). However, prevalent SVD-based approaches overlook the critical phenomenon that decomposition errors exhibit significant disparity across different components of the parameter matrix, often leading to suboptimal approximation. Furthermore, existing methods lack a direct metric to evaluate the importance of individual weight matrices. To address these limitations, we propose **Duo-SVD** (**Du**al-level **O**ptimization **SVD**), a novel training-free framework that synergizes optimization at both the column and the module levels. First, Duo-SVD incorporates a Column-Preserving Strategy that explicitly retains columns exhibiting high decomposition errors, while applying low-rank approximation solely to those with lower errors. Second, at the module level, we employ a Module-Adaptive Allocation Strategy that formulates ratio allocation as a global constrained optimization problem based on perturbation-induced model deviation. Extensive experiments demonstrate that Duo-SVD consistently outperforms state-of-the-art SVD-based baselines and structured pruning methods, establishing it as a superior paradigm for efficient LLM compression.

Paper Type: Long

Research Area: Low-resource Methods for NLP

Research Area Keywords: Efficient/Low-Resource Methods for NLP

Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency

Languages Studied: English

Submission Number: 3776