Art and Design / ETR / Volume 2 / Issue 7 / DOI: 10.61369/ETR.7146
Cite this article
2
Download
14
Citations
83
Views
Journal Browser
Volume | Year
Issue
Search
News and Announcements
View All
ARTICLE

基于ChatGLM 微调的医疗问答系统

杰恺 姚
Show Less
1 广东实验中学, 广东实验中学
ETR 2024 , 2(7), 12–14;
Published: 20 July 2024
© 2024 by the Author(s). Licensee Art and Design, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

为提升大模型在医疗领域的专业性,本文采用Lora微调技术,利用huatuo26M数据集,对ChatGLM3-6B大模型进行微调,构建医疗问答系统。研究结果显示,该方法显著提高了医疗问答的专业度、准确性及对话流畅性。该系统在医疗咨询与健康指导中展现应用价值,并具备推广至其他专业领域大模型微调的潜力。

Keywords
医疗问答系统,ChatGLM 模型,大模型,Lora 微调
References

[1] Du Z, Qian Y, Liu X,et al.GLM:General Language Model Pretraining with Autoregressive Blank Infilling[J].2021.DOI:10.18653/v1/2022.acl-long.26.
[2] 张伟,李明.基于深度学习的医疗问答系统研究综述.计算机工程与应用,2022. 58(12), 1-10.
[3] 王晓霞,刘强.面向医疗领域的自然语言处理技术研究进展.智能科学与技术学报,(2021). 3(2), 152-160.
[4] 赵瑞,陈志军.大型语言模型在医疗领域的应用与挑战.计算机科学,2020.47(6), 1-8.
[5] 李华,张敏.自然语言处理技术在医疗问答系统中的应用.计算机应用研究,2019.36(10), 2925-2930.
[6] Hu E J , Shen Y , Wallis P ,et al.LoRA: Low-Rank Adaptation of Large Language Models[J].2021.DOI:10.48550/arXiv.2106.09685.
[7] Li Jianquan, Wang Xidong, Wu Xiangbo, et al Huatuo-26M: A large-scale Chinese medical question and answer dataset[J],2023.arXiv.https://arxiv.org/abs/2305.01526.

Share
Back to top
Educational Theory and Research, Electronic ISSN: 2995-3456 Print ISSN: 2995-3448, Published by Art and Design