Generative large language models in medicine: a scoping review of recent methodological advances
TL;DR
By tracing the evolutionary trajectories of these methodologies, this scoping review provides a mechanism-centered framework to inform responsible model development and deployment in medical settings, tailored to task complexity, data characteristics, and resource constraints.
Abstract
Generative large language models (LLMs) are rapidly transforming medicine, demonstrating unprecedented capability across a broad spectrum of clinical and biomedical tasks. While prior literature has extensively investigated their applications, the methodological foundation underpinning these models remains comparatively underexamined. In this review, we provide a mechanically grounded analysis of recent methodological advances shaping the development and deployment of generative LLMs in healthcare. We categorize the technical landscape into three principal pillars: pretraining, fine-tuning, and prompt engineering, and examine their key architectures, subtypes, and adaptation strategies based on literature published between 2023 and 2025. We further discuss the emerging directions, including efficient model infrastructures and LLMs-powered multi-agent systems, alongside critical challenges related to bias, generalization, and evaluation. By tracing the evolutionary trajectories of these methodologies, this scoping review provides a mechanism-centered framework to inform responsible model development and deployment in medical settings, tailored to task complexity, data characteristics, and resource constraints.
