A Comprehensive Evaluation of Large Language Models on Benchmark Biomedical Text Processing Tasks

TL;DR

This study evaluates the performance of large language models on biomedical tasks, revealing their potential in low-data scenarios and highlighting variability across models and tasks, despite not surpassing fine-tuned models.

Contribution

First comprehensive evaluation of LLMs on biomedical datasets, comparing their zero-shot capabilities to fine-tuned models across diverse tasks.

Findings

Zero-shot LLMs outperform fine-tuned models on small datasets.

Performance varies significantly among different LLMs and tasks.

LLMs show potential for biomedical tasks with limited annotated data.

Abstract

Recently, Large Language Models (LLM) have demonstrated impressive capability to solve a wide range of tasks. However, despite their success across various tasks, no prior work has investigated their capability in the biomedical domain yet. To this end, this paper aims to evaluate the performance of LLMs on benchmark biomedical tasks. For this purpose, we conduct a comprehensive evaluation of 4 popular LLMs in 6 diverse biomedical tasks across 26 datasets. To the best of our knowledge, this is the first work that conducts an extensive evaluation and comparison of various LLMs in the biomedical domain. Interestingly, we find based on our evaluation that in biomedical datasets that have smaller training sets, zero-shot LLMs even outperform the current state-of-the-art fine-tuned biomedical models. This suggests that pretraining on large text corpora makes LLMs quite specialized even in the biomedical domain. We also find that not a single LLM can outperform other LLMs in all tasks, with the performance of different LLMs may vary depending on the task. While their performance is still quite poor in comparison to the biomedical models that were fine-tuned on large training sets, our findings demonstrate that LLMs have the potential to be a valuable tool for various biomedical tasks that lack large annotated data.