Development of an automatic modification system for generated programs using ChatGPT
Jun Yoshida, Oh Sato, Hane Kondo, Hiroaki Hashiura, Atsuo Hazeyama

TL;DR
This paper presents an automatic system that tests, corrects, and refines code generated by ChatGPT to improve consistency and adherence to program rules, reducing manual effort in code development.
Contribution
It introduces a novel automated modification system for ChatGPT-generated code, enhancing its correctness without human intervention.
Findings
Successfully automated code correction process
Reduced manual effort in code refinement
Improved code consistency and rule adherence
Abstract
In recent years, the field of artificial intelligence has been rapidly developing. Among them, OpenAI's ChatGPT excels at natural language processing tasks and can also generate source code. However, the generated code often has problems with consistency and program rules. Therefore, in this research, we developed a system that tests the code generated by ChatGPT, automatically corrects it if it is inappropriate, and presents the appropriate code to the user. This study aims to address the challenge of reducing the manual effort required for the human feedback and modification process for generated code. When we ran the system, we were able to automatically modify the code as intended.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Healthcare and Education · Online Learning and Analytics · AI in Service Interactions
