Abstract
Low-rank adaptation (LoRA) achieves parameter efficient fine-tuning for large language models (LLMs) by decomposing the model weight update into a pair of low-rank projection matrices. Yet, the memory overhead restricts it to scale up when the model size increases. We propose Randomized LoRA (RLoRA) which adopts Randomized Walsh-Hadamard Transform to achieve significant reduction in the size of trainable parameters compared to LoRA. At the same time, it allows a PAC-Bayes reg-ularizer to be efficiently incorporated to improve generalization. We evaluate the effectiveness of RLoRA on LLMs RoBERTa, GPT-2 and LLaMA-7B using GLUE, E2E and math reasoning benchmarks. With a much lower memory requirement, RLoRA can give similar performance as the SOTA low-rank adaptation methods for these three tasks and significantly better performance under few-shot settings.
Original language | English |
---|---|
Title of host publication | Findings of the Association for Computational Linguistics ACL 2024 |
Editors | Lun-Wei Ku, Andre Martins, Vivek Srikumar |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 5236-5249 |
Number of pages | 14 |
ISBN (Electronic) | 9798891760998 |
DOIs | |
Publication status | Published - Aug 2024 |
Event | 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 - Bangkok, Thailand Duration: 11 Aug 2024 → 16 Aug 2024 https://2024.aclweb.org/ https://aclanthology.org/events/acl-2024/ |
Publication series
Name | Proceedings of the Annual Meeting of the Association for Computational Linguistics |
---|---|
ISSN (Print) | 0736-587X |
Conference
Conference | 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 |
---|---|
Country/Territory | Thailand |
City | Bangkok |
Period | 11/08/24 → 16/08/24 |
Internet address |
Scopus Subject Areas
- Computer Science Applications
- Linguistics and Language
- Language and Linguistics