Prompt Engineering with GPT3.5 for Enhancing Information Extraction in Medical Texts

Poster Number: P09
Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Information Extraction, Natural Language Processing, Large Language Models (LLMs)
Primary Track: Foundations
Programmatic Theme: Academic Informatics / LIEAF

We explore the viability of employing GPT-3.5 for the extraction of biomedical named entities from biomedical texts dataset by incorporating different prompt-based strategies. The results show an improvement on F1-score over five NER datasets after appropriate prompt engineering improvements. Our findings indicate that utilizing LLMs as a joint source of prior knowledge can be a viable approach for improving the state of the art for few-shot learning-based NER in medical text.

Speaker(s):
Yao Ge, Master
Emory University