In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
Special Topics in Development and Application of Large Language model
|
App. Res. of Comp. Printed Article
Vol. 41, 2024 No. 10
2906-2910

Two-phases fine-tuning of professional large language model via clinical data

Sun Liping1,2
Tong Zilong3
Qian Qian3
Lu Xintao3
Ling Chen1
Fang Cheng4
Tang Qiyu4
Jiang Xiao5
1. Medical Instrumentation College, Shanghai University of Medicine & Health Sciences, Shanghai 201318, China
2. School of Information Science & Technology, Fudan University, Shanghai 200433, China
3. School of Health Sciences & Engineering, University of Shanghai for Science & Technology, Shanghai 200093, China
4. Third Affiliated Hospital of Naval Medical University, Shanghai 200438, China
5. 905th Hospital of PLA, Shanghai 200052, China
DOI: 10.19734/j.issn.1001-3695.2024.03.0071

Abstract

General large language model(LLM) lacks the depth and breadth of understanding of domain-specific knowledge, resulting in insufficient accuracy in addressing domain-specific questions and often leading to illusions, which hinders the commercial deployment of large language models. Therefore, enhancing the professionalism of large language models based on domain-specific data has become a key challenge for the practical application of large language models. This study aimed to address the issue of insufficient domain-specific knowledge understanding and content professionalism of general large language models in specific domains. This paper proposed a two-stage fine-tuning framework for professional large language models based on the efficient parameter fine-tuning methods of P-Tuning v2 and Freeze. This framework, relying on clinical data from hepatobiliary specialties, fine-tuned ChatGLM-6B to obtain a professional-level large language model for hepatobiliary specialties, named MedGLM. H. According to the experiments, the fine-tuned large language model exhibited an increase in accuracy for hepatobiliary specialist questions from 31% to 62%, and the scoring rate increased from 57% to 73%. After two-phase fine-tuning, the model demonstrates higher accuracy and professionalism in hepatobiliary specialty QA. Dialogue experiments conducted with three clinical doctors confirm the application potential of the fine-tuned model in more specialized medical scenarios.

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.03.0071
Publish at: Application Research of Computers Printed Article, Vol. 41, 2024 No. 10
Section: Special Topics in Development and Application of Large Language model
Pages: 2906-2910
Serial Number: 1001-3695(2024)10-004-2906-05

Publish History

[2024-10-05] Printed Article

Cite This Article

孙丽萍, 童子龙, 钱乾, 等. 基于医疗临床数据的两阶段专业级大语言模型微调 [J]. 计算机应用研究, 2024, 41 (10): 2906-2910. (Sun Liping, Tong Zilong, Qian Qian, et al. Two-phases fine-tuning of professional large language model via clinical data [J]. Application Research of Computers, 2024, 41 (10): 2906-2910. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)