META-LORA: Memory-Efficient Sample Reweighting for Fine-Tuning Large Language Models

Weicheng Li, Lixin Zou, Min Tang, Qing Yu, Wanli Li, Chenliang Li


Abstract
Supervised fine-tuning (SFT) is widely adopted for tailoring large language models (LLMs) to specific downstream tasks. However, the substantial computational demands of LLMs hinder iterative exploration of fine-tuning datasets and accurate evaluation of individual sample importance. To address this challenge, we introduce Meta-LoRA, a memory-efficient method for automatic sample reweighting. Meta-LoRA learns to reweight fine-tuning samples by minimizing the loss on a small, high-quality validation set through an end-to-end bi-level optimization framework based on meta-learning. To reduce memory usage associated with computing second derivatives, we approximate the bi-level optimization using gradient similarity between training and validation datasets, replacing bi-dimensional gradient similarity with the product of one-dimensional activation states and their corresponding gradients. Further memory optimization is achieved by refining gradient computations, selectively applying them to the low-rank layers of LoRA, which results in as little as 4% additional memory usage. Comprehensive evaluations across benchmark datasets in mathematics, coding, and medical domains demonstrate Meta-LoRA’s superior efficacy and efficiency. The source code is available at https://github.com/liweicheng-ai/meta-lora.
Anthology ID:
2025.coling-main.568
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8504–8517
Language:
URL:
https://aclanthology.org/2025.coling-main.568/
DOI:
Bibkey:
Cite (ACL):
Weicheng Li, Lixin Zou, Min Tang, Qing Yu, Wanli Li, and Chenliang Li. 2025. META-LORA: Memory-Efficient Sample Reweighting for Fine-Tuning Large Language Models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8504–8517, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
META-LORA: Memory-Efficient Sample Reweighting for Fine-Tuning Large Language Models (Li et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.568.pdf