Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models

TL;DR

This paper introduces ClinGen, a knowledge-infused prompting method for synthetic clinical text generation using large language models, improving performance and diversity in clinical NLP tasks while addressing privacy and resource constraints.

Contribution

The paper presents ClinGen, a novel, resource-efficient approach that infuses domain knowledge into LLM prompting for clinical text generation, advancing NLP performance and diversity.

Findings

ClinGen improves performance across 7 clinical NLP tasks.

Generated data better matches real dataset distributions.

Significantly increases diversity of training data.

Abstract

Clinical natural language processing requires methods that can address domain-specific challenges, such as complex medical terminology and clinical contexts. Recently, large language models (LLMs) have shown promise in this domain. Yet, their direct deployment can lead to privacy issues and are constrained by resources. To address this challenge, we delve into synthetic clinical text generation using LLMs for clinical NLP tasks. We propose an innovative, resource-efficient approach, ClinGen, which infuses knowledge into the process. Our model involves clinical knowledge extraction and context-informed LLM prompting. Both clinical topics and writing styles are drawn from external domain-specific knowledge graphs and LLMs to guide data generation. Our extensive empirical study across 7 clinical NLP tasks and 16 datasets reveals that ClinGen consistently enhances performance across various tasks, effectively aligning the distribution of real datasets and significantly enriching the diversity of generated training instances. Our code is available at \url{https://github.com/ritaranx/ClinGen}.