EUVIMEDEUVIMED entdecken
Crossref

Fine-Tuning Pre-Trained language models for Vietnamese: A comparative study of full fine-tuning and Lora

Xanh Van Nguyen, Hao Nhat Van Luu, Hung Dinh, Hoa Minh Dinh

Tạp chí Khoa học HUFLIT · 27.10.2025 · 9 (3) · 36

DOI: 10.71091/2354-113x/275 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tạp chí Khoa học HUFLIT, online erschienen am 27.10.2025. Verfasst von Xanh Van Nguyen und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pre-trained language models have brought significant improvements to Vietnamese natural language processing tasks. However, full fine-tuning of these large models remains resource-intensive and poses challenges for settings with limited computational capacity. This paper presents a comparative study between full fine-tuning and Low-Rank Adaptation – a parameter-efficient fine-tuning method, focusing on the trade-off between model performance and resource usage. Experiments are conducted on two core NLP tasks – sentiment analysis and named entity recognition – using benchmark Vietnamese datasets and pre-trained models such as PhoBERT, BARTpho and ViT5. The results show that LoRA achieves comparable accuracy to full fine-tuning while significantly reducing training cost, especially in transformer-based architectures. These findings suggest that LoRA is a viable and efficient alternative to full fine-tuning for fine-tuning Vietnamese PLMs in low-resource environments. Our work provides practical insights and experimental benchmarks to support informed decision-making in selecting fine-tuning strategies for Vietnamese NLP applications.

Zitieren

APA

Nguyen, X. V., Luu, H. N. V., Dinh, H., & Dinh, H. M. (2025). Fine-Tuning Pre-Trained language models for Vietnamese: A comparative study of full fine-tuning and Lora. Tạp chí Khoa học HUFLIT, 9(3), 36. https://doi.org/10.71091/2354-113x/275

Vancouver

Nguyen XV, Luu HNV, Dinh H, Dinh HM. Fine-Tuning Pre-Trained language models for Vietnamese: A comparative study of full fine-tuning and Lora. Tạp chí Khoa học HUFLIT. 2025;9(3):36. doi:10.71091/2354-113x/275

BibTeX
@article{Nguyen2025,
  author = {Nguyen, Xanh Van and Luu, Hao Nhat Van and Dinh, Hung and Dinh, Hoa Minh},
  title = {Fine-Tuning Pre-Trained language models for Vietnamese: A comparative study of full fine-tuning and Lora},
  journal = {Tạp chí Khoa học HUFLIT},
  year = {2025},
  volume = {9},
  number = {3},
  pages = {36},
  doi = {10.71091/2354-113x/275}
}
Kostenlos starten →