Intelligent Understanding of Large Language Models in Traditional Chinese Medicine Based on Prompt Engineering Framework

TL;DR

This paper introduces TCM-Prompt, a prompt engineering framework that significantly improves large language models' performance in Traditional Chinese Medicine tasks, facilitating domain-specific applications and advancements.

Contribution

The paper presents a novel prompt engineering framework tailored for TCM, integrating multiple techniques to enhance LLM performance in specialized medical NLP tasks.

Findings

Demonstrated superior accuracy in disease classification and syndrome identification.

Showed improved herbal medicine recommendation quality.

Validated effectiveness across various TCM-related NLP tasks.

Abstract

This paper explores the application of prompt engineering to enhance the performance of large language models (LLMs) in the domain of Traditional Chinese Medicine (TCM). We propose TCM-Prompt, a framework that integrates various pre-trained language models (PLMs), templates, tokenization, and verbalization methods, allowing researchers to easily construct and fine-tune models for specific TCM-related tasks. We conducted experiments on disease classification, syndrome identification, herbal medicine recommendation, and general NLP tasks, demonstrating the effectiveness and superiority of our approach compared to baseline methods. Our findings suggest that prompt engineering is a promising technique for improving the performance of LLMs in specialized domains like TCM, with potential applications in digitalization, modernization, and personalized medicine.