PGSB: Pretrained-Guided Shared Basis for LoRA Model Merging

arXiv:2610.14558v1 Announce Type: new Abstract: Large pretrained models have achieved remarkable success across diverse domains, yet adapting them to multiple downstream tasks remains challenging: full fine-tuning is costly, while maintaining separate task-specific models is storage-inefficient and fails to produce a unified multi-task model. Low-Rank Adaptation (LoRA) offers an efficient alternative for Model Merging by representing each task adaptation as a low-rank update over frozen pretrained weights. However, existing LoRA merging methods often treat task-specific updates as directly comparable objects and merge them in their original low-rank parameter spaces. This overlooks two key factors: which update directions provide reliable shared support across tasks, and how these directions should be re-parameterized with respect to the pretrained weights before merging. To address this limitation, we propose Pretrained-Guided Shared Basis (PGSB), a two-stage framework for LoRA model merging. PGSB first identifies shared directions among task-specific LoRA updates, and then re-parameterizes these directions using their interaction with the pretrained weights, producing a more suitable basis for merging. Extensive experiments demonstrate that PGSB consistently outperforms state-of-the-art baselines across multiple benchmarks. Codes are available at https://github.com/Kitschnada/Pretrained-Basis .

Related

• When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning
• Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning
• SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression

Source: arXiv cs.LG | 2026-10-14