| |
Elevating Automated Software Maintenance Tasks with Large Language Models |  | ZHOU Xin PhD Candidate
School of Computing and Information Systems
Singapore Management University
| Research Area Dissertation Committee Research Advisor Dissertation Committee Members External Member - XING Zhenchang, Senior Principal Research Scientist and Honorary Associate Professor, CSIRO’s Data61 and Australian National University
|
| | Date 25 November 2024 (Monday) | Time 10:00am – 11:00am | Venue Meeting Room 4.4,
Level 4
School of Computing and Information Systems 1, Singapore Management University, 80 Stamford Road Singapore 178902 | Please register by 24 November 2024. We look forward to seeing you at this research seminar. 
|
|
|
| | ABOUT THE TALK Software engineering involves many tasks across different phases such as requirements, design, implementation, testing, and maintenance. Among them, software maintenance is a crucial phase. To boost developer productivity, in recent years, numerous research endeavors in software engineering have sought to automate certain software maintenance tasks. This dissertation presents a series of works aimed at advancing automated solutions for software maintenance by leveraging and enhancing LLMs.
In the first study of this dissertation, we propose a new LLM specifically designed for code changes, namely CCBERT, which captures fine-grained changes at the token level. In the second study, we present VulMaster, a framework designed to enhance the effectiveness of LLMs in vulnerability repair. In the third study, we present LLM4PatchCorrect, an LLM-based approach for assessing patch correctness. In the fourth study, we investigate the impact of long-tailed distributions on the performance of popular LLMs, especially in software maintenance tasks like automatic code review and vulnerability type prediction.
In conclusion, this dissertation contributes to the Software Engineering field by demonstrating the potential of large language models (LLMs) to enhance software maintenance tasks. | | | ABOUT THE SPEAKER Xin ZHOU conducts research in software engineering, focusing on leveraging and enhancing large language models to reduce the labor intensity of software engineering tasks and alleviate developers' workload. Before joining SMU, Xin graduated with a Bachelor’s degree from Beijing Institute of Technology, China. In his leisure time, he enjoys sports and reading. |
|
