DPLoRA: A Dual-Pruning Framework based on ILP Optimization and Progressive Pruning for Parameter-Efficient LoRA Fine-Tuning

Changjun Park, Sejong Yoon, Jaekwang Kim


Abstract
We propose DPLoRA (Dual-Pruning Low-Rank Adaptation), a framework that optimizes rank allocation via two stages: (1) an initial pruning stage (OPLoRA; Optimal Pruning LoRA) that uses Integer Linear Programming (ILP) to determine optimal layer-wise ranks without manual tuning; and (2) a progressive pruning stage that further reduces ranks adaptively during training using importance scores smoothed by Exponential Moving Average (EMA). Experiments demonstrate that OPLoRA consistently outperforms existing PEFT baselines on GLUE and instruction-following tasks, while the full DPLoRA framework establishes a new state-of-the-art among compared PEFT baselines on GLUE at high-performance settings (p=0.4). At efficiency-focused settings (p=0.8), our method reduces trainable parameters by over 80% and training time by 46% compared to standard LoRA, offering a highly efficient solution for deploying large-scale models in resource-constrained environments.
Anthology ID:
2026.findings-acl.1693
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
33892–33908
Language:
URL:
https://aclanthology.org/2026.findings-acl.1693/
DOI:
10.18653/v1/2026.findings-acl.1693
Bibkey:
Cite (ACL):
Changjun Park, Sejong Yoon, and Jaekwang Kim. 2026. DPLoRA: A Dual-Pruning Framework based on ILP Optimization and Progressive Pruning for Parameter-Efficient LoRA Fine-Tuning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 33892–33908, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
DPLoRA: A Dual-Pruning Framework based on ILP Optimization and Progressive Pruning for Parameter-Efficient LoRA Fine-Tuning (Park et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1693.pdf
Checklist:
 2026.findings-acl.1693.checklist.pdf