English

Revisiting the Impact of Pursuing Modularity for Code Generation

Computation and Language 2024-11-04 v3

Abstract

Modular programming, which aims to construct the final program by integrating smaller, independent building blocks, has been regarded as a desirable practice in software development. However, with the rise of recent code generation agents built upon large language models (LLMs), a question emerges: is this traditional practice equally effective for these new tools? In this work, we assess the impact of modularity in code generation by introducing a novel metric for its quantitative measurement. Surprisingly, unlike conventional wisdom on the topic, we find that modularity is not a core factor for improving the performance of code generation models. We also explore potential explanations for why LLMs do not exhibit a preference for modular code compared to non-modular code.

Keywords

Cite

@article{arxiv.2407.11406,
  title  = {Revisiting the Impact of Pursuing Modularity for Code Generation},
  author = {Deokyeong Kang and Ki Jung Seo and Taeuk Kim},
  journal= {arXiv preprint arXiv:2407.11406},
  year   = {2024}
}

Comments

EMNLP 2024 Findings

R2 v1 2026-06-28T17:42:33.530Z