Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models

TL;DR

This paper investigates coding style differences between large language models and human programmers, revealing inconsistencies and proposing solutions to improve code quality and consistency.

Contribution

It provides an empirical analysis of coding style inconsistencies in LLM-generated code and offers a taxonomy and potential solutions for addressing these issues.

Findings

LLMs and humans exhibit different coding styles.

Coding style inconsistencies affect readability, conciseness, and robustness.

Proposed solutions can mitigate style inconsistencies.

Abstract

Large language models (LLMs) have brought a paradigm shift to the field of code generation, offering the potential to enhance the software development process. However, previous research mainly focuses on the accuracy of code generation, while coding style differences between LLMs and human developers remain under-explored. In this paper, we empirically analyze the differences in coding style between the code generated by mainstream Code LLMs and the code written by human developers, and summarize coding style inconsistency taxonomy. Specifically, we first summarize the types of coding style inconsistencies by manually analyzing a large number of generation results. We then compare the code generated by Code LLMs with the code written by human programmers in terms of readability, conciseness, and robustness. The results reveal that LLMs and developers have different coding styles. Additionally, we study the possible causes of these inconsistencies and provide some solutions to alleviate the problem.