EMNLP Findings2024
Revisiting the Impact of Pursuing Modularity for Code Generation
Deokyeong Kang, Ki Jung Seo, Taeuk Kim
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. Our code is available at https://github.com/HYU-NLP/Revisiting- Modularity.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on1
Related papers
- Aligning Offline Metrics and Human Judgments of Value for Code Generation ModelsVictor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh et al.ACL Findings 2023 · 11 citations
- Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language ModelsYanlin Wang, Tianyue Jiang, Mingwei Liu, Jiachi Chen et al.FSE 2025 · 6 citations
- Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?Bonan Kou, Shengmai Chen, Zhijie Wang, Lei Ma et al.FSE 2024 · 8 citations
- Rethinking Code Complexity Through the Lens of Large Language ModelsChen Xie, Xiaodong Gu, Yuling Shi, Beijun ShenICML 2026
- MoT: Modularization-of-Thought Prompting for Effective Code GenerationRuwei Pan, Hongyu ZhangISSTA 2026
