Saved in:
Bibliographic Details
Main Authors: Monajatipoor, Masoud, Yang, Jiaxin, Stremmel, Joel, Emami, Melika, Mohaghegh, Fazlolah, Rouhsedaghat, Mozhdeh, Chang, Kai-Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.07376
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911951816228864
author Monajatipoor, Masoud
Yang, Jiaxin
Stremmel, Joel
Emami, Melika
Mohaghegh, Fazlolah
Rouhsedaghat, Mozhdeh
Chang, Kai-Wei
author_facet Monajatipoor, Masoud
Yang, Jiaxin
Stremmel, Joel
Emami, Melika
Mohaghegh, Fazlolah
Rouhsedaghat, Mozhdeh
Chang, Kai-Wei
contents Large Language Models (LLMs) demonstrate remarkable versatility in various NLP tasks but encounter distinct challenges in biomedical due to the complexities of language and data scarcity. This paper investigates LLMs application in the biomedical domain by exploring strategies to enhance their performance for the NER task. Our study reveals the importance of meticulously designed prompts in the biomedical. Strategic selection of in-context examples yields a marked improvement, offering ~15-20\% increase in F1 score across all benchmark datasets for biomedical few-shot NER. Additionally, our results indicate that integrating external biomedical knowledge via prompting strategies can enhance the proficiency of general-purpose LLMs to meet the specialized needs of biomedical NER. Leveraging a medical knowledge base, our proposed method, DiRAG, inspired by Retrieval-Augmented Generation (RAG), can boost the zero-shot F1 score of LLMs for biomedical NER. Code is released at \url{https://github.com/masoud-monajati/LLM_Bio_NER}
format Preprint
id arxiv_https___arxiv_org_abs_2404_07376
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLMs in Biomedicine: A study on clinical Named Entity Recognition
Monajatipoor, Masoud
Yang, Jiaxin
Stremmel, Joel
Emami, Melika
Mohaghegh, Fazlolah
Rouhsedaghat, Mozhdeh
Chang, Kai-Wei
Computation and Language
Large Language Models (LLMs) demonstrate remarkable versatility in various NLP tasks but encounter distinct challenges in biomedical due to the complexities of language and data scarcity. This paper investigates LLMs application in the biomedical domain by exploring strategies to enhance their performance for the NER task. Our study reveals the importance of meticulously designed prompts in the biomedical. Strategic selection of in-context examples yields a marked improvement, offering ~15-20\% increase in F1 score across all benchmark datasets for biomedical few-shot NER. Additionally, our results indicate that integrating external biomedical knowledge via prompting strategies can enhance the proficiency of general-purpose LLMs to meet the specialized needs of biomedical NER. Leveraging a medical knowledge base, our proposed method, DiRAG, inspired by Retrieval-Augmented Generation (RAG), can boost the zero-shot F1 score of LLMs for biomedical NER. Code is released at \url{https://github.com/masoud-monajati/LLM_Bio_NER}
title LLMs in Biomedicine: A study on clinical Named Entity Recognition
topic Computation and Language
url https://arxiv.org/abs/2404.07376