The Evolving Landscape of Generative Large Language Models and Traditional Natural Language Processing in Medicine

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.

@article{yang2025_2505.10261,
  title={ The Evolving Landscape of Generative Large Language Models and Traditional Natural Language Processing in Medicine },
  author={ Rui Yang and Huitao Li and Matthew Yu Heng Wong and Yuhe Ke and Xin Li and Kunyu Yu and Jingchi Liao and Jonathan Chong Kai Liew and Sabarinath Vinod Nair and Jasmine Chiat Ling Ong and Irene Li and Douglas Teodoro and Chuan Hong and Daniel Shu Wei Ting and Nan Liu },
  journal={arXiv preprint arXiv:2505.10261},
  year={ 2025 }
}