RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognition.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date: Sep 1, 2024

Abstract

OBJECTIVES: This article aims to enhance the performance of larger language models (LLMs) on the few-shot biomedical named entity recognition (NER) task by developing a simple and effective method called Retrieving and Chain-of-Thought (RT) framework and to evaluate the improvement after applying RT framework.

Authors

  • Mingchen Li
    Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, MN, USA.
  • Huixue Zhou
    Institute for Health Informatics, University of Minnesota, Minneapolis, Minnesota, USA.
  • Han Yang
    Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China.
  • Rui Zhang
    Department of Cardiology, Zhongda Hospital, Medical School of Southeast University, Nanjing, China.

Keywords

External Resources

Popular Topics
Recent Journals