«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

34

期数:

2024年06期

页码:

178-184

栏目:

新型计算应用系统

出版日期:

2024-06-10

文章信息/Info

Title:

MedKGGPT:A Design Method for Medical Large Language Models Based on Knowledge Graphs

文章编号:

1673-629X(2024)06-0178-07

作者:

顾鹏辉1; 李涛1; 2; 高阳1

1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065;2. 武汉科技大学 智能信息处理与实时工业系统湖北省重点实验室,湖北 武汉 430065

Author(s):

GU Peng-hui1; LI Tao1; 2; GAO Yang1

1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;2. Hubei Province Key Laboratory of Intelligent Information Processingand Real-time Industrial System,Wuhan University of Science and Technology,Wuhan 430065,China

关键词:

大型语言模型; 医疗; 知识图谱; 提示工程; ChatGLM

Keywords:

large language models; medicine; knowledge graph; prompt engineering; ChatGLM

分类号:

TP391

DOI:

10.20165/j.cnki.ISSN1673-629X.2024.0073

摘要:

大型语言模型(Large Language Models,LLM)已经成为现今主流的研究热点,而垂直领域行业大模型则成为落地应用的关键点,以医疗为代表的大型语言模型有着可解释性、可靠性、高安全性等要求。 针对这类问题,提出 MedKGGPT 模型,一个基于 ChatGLM 的模型,并提出一种面向医疗领域的知识图谱(Knowledge Graphs,KGs)和 LLM 相结合的框架。 框架主要包含两个部分:首先,通过 KG 三元组中的实体和关系,提出了一种基于 KG 结构数据的提示工程方法,使得 LLM 更加具有医学领域的专用知识,提高 LLM 的可解释性;其次,提出一种利用 KG 来对齐 LLM 的方法,将 LLM 的输出与 KG 的相关知识进行比较,验证 LLM 输出结果的一致性和准确性,从而增强了 LLM 在医疗领域的安全性。 实验结果表明,最终生成的 MedKGGPT 模型能够输出更加具有安全性的结果,说明 KG 能够有效增强 LLM 的可解释性,为 LLM 应用在医疗领域提供了帮助。

Abstract:

Large Language Models (LLMs) have become a mainstream research focus,while large models in vertical industries have become the key to practical applications. LLMs,represented by the medical field,require interpretability,reliability,and high security. To address these issues, we propose the MedKGGPT, a model based on ChatGLM, and a framework that combines Knowledge Graphs (KGs) and LLMs specifically for the medical field. The framework mainly contains two parts. Firstly,through the entities and relationships in the triples of the KGs,we propose a prompt engineering method based on the structural data of the KGs,which makes the LLM more specialized in medical knowledge and improves the LLM’s interpretability. Secondly,we propose a method of aligning the LLM with the KGs. This involves comparing the output of the LLM with the related knowledge in the KGs,verifying the consistency and accuracy of the LLM output,thereby enhancing the security of the LLM in the medical field. Experimental results demonstrate that the final MedKGGPT can output more secure results. It is indicated that KGs can effectively enhance the interpretability of the LLM, providing assistance for the application of LLMs in the medical field.

常用功能

更新日期/Last Update: 2024-06-10