Improving large language models for clinical named entity recognition via prompt engineering
245 Citations•2024•
Yan Hu, Qingyu Chen, Jingcheng Du
A clinical task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications and suggests a promising direction in leveraging LLMs for clinical NER tasks.
Abstract
While direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.