articleACM Transactions on Software Engineering and MethodologyJan 27, 2024BRONZE OA

Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues

YLYue LiuTLThanh Le-CongRWRatnadira WidyasariCTChakkrit TantithamthavornLLLi Li

Monash University · Singapore Management University · +2 more institutions

Indexed incrossref

Abstract

Since its introduction in November 2022, ChatGPT has rapidly gained popularity due to its remarkable ability in language understanding and human-like responses. ChatGPT, based on GPT-3.5 architecture, has shown great promise for revolutionizing various research fields, including code generation. However, the reliability and quality of code generated by ChatGPT remain unexplored, raising concerns about potential risks associated with the widespread use of ChatGPT-driven code generation. In this article, we systematically study the quality of 4,066 ChatGPT-generated programs of code implemented in two popular programming languages, i.e., Java and Python, for 2,033 programming tasks. The goal of this work is…

Citation impact

113
total citations
FWCI
11.94
Percentile
100%
References
48
Citations per year

Authors

7

Topics & keywords

Topics
Keywords
  • Computer science
  • Refining (metallurgy)
  • Code (set theory)
  • Quality (philosophy)
  • Programming language
  • Chemistry
No related works found for this paper.

Funding