Weicheng Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Weicheng Wang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Aijia Ouyang
Zunyi Normal University
1 shared publication - Jianguo Chen
School of Safety Science, Tsinghua University, Beijing 100084, China
1 shared publication - Wenqing Chen
School of Software Engineering, Sun Yat-sen University, Zhuhai, China
1 shared publication - Xiangyuan Zhu
Zhaoqing University
1 shared publication - Zeju Cai
School of Software Engineering and Zhuhai Key Laboratory of Trusted Large Language Models, Sun Yat-sen University, Guangzhou, China
1 shared publication
Latest Publications
- Open Access
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 416-417
F-CodeLLM: A Federated Learning Framework for Adapting Large Language Models to Practical Software Development
Large Language Models (LLMs) have revolutionized code intelligence tasks, but their performance in specific software development tasks often requires fine-tuning with task-specific data. However, acquiring such data is challenging due to privacy concerns. We introduce F-CodeLLM, a novel federated learning framework for adapting LLMs to software development tasks while preserving code data privacy. Leveraging federated learning and LoRA-based efficient fine-tuning, F-CodeLLM allows organizations to collaboratively improve LLMs without sharing sensitive data. Our experiments demonstrate that F-CodeLLM achieves comparable results to centralized fine-tuning methods and excels in multi-language environments, marking a significant advancement in the application of LLMs for software engineering.
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 416-417
Open AccessF-CodeLLM: A Federated Learning Framework for Adapting Large Language Models to Practical Software Development
Large Language Models (LLMs) have revolutionized code intelligence tasks, but their performance in specific software development tasks often requires fine-tuning with task-specific data. However, acquiring such data is challenging due to privacy concerns. We introduce F-CodeLLM, a novel federated learning framework for adapting LLMs to software development tasks while preserving code data privacy. Leveraging federated learning and LoRA-based efficient fine-tuning, F-CodeLLM allows organizations to collaboratively improve LLMs without sharing sensitive data. Our experiments demonstrate that F-CodeLLM achieves comparable results to centralized fine-tuning methods and excels in multi-language environments, marking a significant advancement in the application of LLMs for software engineering.