The Evolving Landscape of Generative Large Language Models and Traditional Natural Language Processing in Medicine
This work addresses the underexplored differences between generative LLMs and traditional NLP across medical tasks, which is incremental as it compares existing methods on known data.
The study analyzed 19,123 studies to compare generative large language models (LLMs) and traditional natural language processing (NLP) in medicine, finding that generative LLMs excel in open-ended tasks while traditional NLP is better for information extraction and analysis tasks.
Natural language processing (NLP) has been traditionally applied to medicine, and generative large language models (LLMs) have become prominent recently. However, the differences between them across different medical tasks remain underexplored. We analyzed 19,123 studies, finding that generative LLMs demonstrate advantages in open-ended tasks, while traditional NLP dominates in information extraction and analysis tasks. As these technologies advance, ethical use of them is essential to ensure their potential in medical applications.