Fine-tuning large language models for domain-specific tasks such as medical text summarization demands substantial computational resources. Parameter-efficient fine-tuning (PEFT) methods offer promising alternatives by updating only a small fraction of parameters. This paper compares three adaptation approaches-Low-Rank Adaptation (LoRA), Prompt Tuning, and Full Fine-Tuning-across the Flan-T5 model family on the PubMed medical summarization dataset. Through experiments with multiple random seeds, we demonstrate that LoRA consistently outperforms full fine-tuning, achieving 43.52 +/- 0.18 ROUGE-1 on Flan-T5-Large with only 0.6% trainable parameters compared to 40.67 +/- 0.21 for full fine-tuning. Sensitivity analyses examine the impact of LoRA rank and prompt token count. Our findings suggest the low-rank constraint provides beneficial regularization, challenging assumptions about the necessity of full parameter updates. Code is available at https://github.com/eracoding/llm-medical-summarization
@article{arxiv.2603.21970,
title = {Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning},
author = {Ulugbek Shernazarov and Rostislav Svitsov and Bin Shi},
journal= {arXiv preprint arXiv:2603.21970},
year = {2026}
}
Comments
9 pages, 5 figures, presented at 6th International Conference on NLP & Text Mining (NLTM 2026), March 21-22, Sydney, Australia. Published in Computer Science & Information Technology (CS & IT), pp. 01-09, 2026