Refining ChatGPT-generated code: Characterizing and mitigating code quality issues

• Main Authors: LIU, Yue, LE-CONG, Thanh, RATNADIRA WIDYASARI, LO, David
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Automated code generation; ChatGPT; code analysis; Artificial Intelligence and Robotics; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/9242; https://ink.library.smu.edu.sg/context/sis_research/article/10242/viewcontent/3643674.pdf
• Institution: Singapore Management University

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. How...