Unveiling the potential of large language models in generating semantic and cross-language clones

TL;DR

This paper evaluates GPT-3's ability to generate semantic and cross-language code clones, demonstrating promising accuracy and potential for aiding code reuse, comprehension, and refactoring across different programming languages.

Contribution

It introduces a novel evaluation of GPT-3 for semantic and cross-language clone generation using SemanticCloneBench, highlighting its strengths and challenges in this domain.

Findings

GPT-3 achieves 62.14% accuracy in semantic clone generation.

GPT-3 attains 91.25% accuracy in cross-language clone generation.

Few-shot prompt engineering enhances GPT-3's code variant quality.

Abstract

Semantic and Cross-language code clone generation may be useful for code reuse, code comprehension, refactoring and benchmarking. OpenAI's GPT model has potential in such clone generation as GPT is used for text generation. When developers copy/paste codes from Stack Overflow (SO) or within a system, there might be inconsistent changes leading to unexpected behaviours. Similarly, if someone possesses a code snippet in a particular programming language but seeks equivalent functionality in a different language, a semantic cross-language code clone generation approach could provide valuable assistance. In this study, using SemanticCloneBench as a vehicle, we evaluated how well the GPT-3 model could help generate semantic and cross-language clone variants for a given fragment.We have comprised a diverse set of code fragments and assessed GPT-3s performance in generating code variants.Through extensive experimentation and analysis, where 9 judges spent 158 hours to validate, we investigate the model's ability to produce accurate and semantically correct variants. Our findings shed light on GPT-3's strengths in code generation, offering insights into the potential applications and challenges of using advanced language models in software development. Our quantitative analysis yields compelling results. In the realm of semantic clones, GPT-3 attains an impressive accuracy of 62.14% and 0.55 BLEU score, achieved through few-shot prompt engineering. Furthermore, the model shines in transcending linguistic confines, boasting an exceptional 91.25% accuracy in generating cross-language clones