Shunfu Jin

Prof. Shunfu Jin

orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

22 March 2022 in Journal of Systems Science and Systems Engineering
Verified
Journal Article
Closed access
PDF file
HWHaixing Wu
Haixing Wu
SJShunfu Jin
Shunfu Jin
WYWuyi Yue
Wuyi Yue

11 September 2024
Verified
Conference Paper
Open access
BYBoyang Yang
Boyang Yang
HTHaoye Tian
Haoye Tian
WPWeiguo Pian
Weiguo Pian
HYHaoran Yu
Haoran Yu
HWHaitao Wang
Haitao Wang
SJShunfu Jin
Shunfu Jin
With the proven effectiveness of Large Language Models (LLMs) in code-related tasks, researchers have explored their potential for program repair. However, existing repair benchmarks might have influenced LLM training data, potentially causing data leakage. To evaluate LLMs’ realistic repair capabilities, (i) we introduce an extensive, non-crawled benchmark TutorCode, comprising 1,239 C++ defect codes and associated information such as tutor guidance, solution description, failing test cases, and the corrected code. Our work assesses LLM’s repair performance on TutorCode, measuring repair correctness (TOP-5 and AVG-5) and patch precision (RPSR). (ii) We then provide a comprehensive investigation into which types of extra information can help LLMs improve their repair performance. Among these types, tutor guidance was the most effective information. To fully harness LLMs’ conversational capabilities and the benefits of augmented information, (iii) we introduce a novel conversational semi-automatic repair framework CREF assisting human programming tutors. It demonstrates a remarkable AVG-5 improvement of 17.2%-24.6% compared to the baseline, achieving an impressive AVG-5 of 76.6% when utilizing GPT-4. These results highlight the potential for enhancing LLMs’ repair capabilities through tutor interactions and historical conversations. The successful application of CREF in a real-world educational setting demonstrates its effectiveness in reducing tutors’ workload and improving students’ learning experience, showing promise for code review and other software engineering tasks.

7 November 2023 in Information Sciences
Verified
Journal Article
Closed access
HWHaixing Wu
Haixing Wu
JGJingwei Geng
Jingwei Geng
XBXiaojun Bai
Xiaojun Bai
SJShunfu Jin
Shunfu Jin

1 January 2022 in International Journal of Applied Mathematics and Computer Science
Verified
Journal Article
Open access
PDF file
HZHuan Zheng
Huan Zheng
SJShunfu Jin
Shunfu Jin
Mobile edge computing (MEC) is one of the key technologies to achieve high bandwidth, low latency and reliable service in fifth generation (5G) networks. In...