Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning

TL;DR

This study compares parameter-efficient fine-tuning methods for medical text summarization, finding LoRA outperforms full fine-tuning in accuracy while using significantly fewer trainable parameters.

Contribution

It provides a comprehensive comparison of LoRA, Prompt Tuning, and Full Fine-Tuning on medical summarization, highlighting LoRA's superior performance and efficiency.

Findings

LoRA achieves higher ROUGE-1 scores than full fine-tuning.

LoRA uses only 0.6% of trainable parameters compared to full fine-tuning.

Low-rank regularization benefits model performance.

Abstract

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