Standards guided approach improves code documentation quality
Standards-Guided and Dependency-Aware Code-Level Documentation Generation
Software Engineering
Summary
Creating good documentation for software is hard because many tools just guess what to write without clear rules. The authors argue that documentation should follow strong quality standards and understand how code pieces depend on one another. They built a system called CODEDOC that uses those standards and code relationships to generate better explanations of functions and classes. Tests showed CODEDOC writes clearer docs faster and judges its work well compared to other tools. People also agreed that CODEDOC’s evaluations matched human opinions closely.
What this means in practice
- •For python developers: Generate clear, standards-aligned documentation for Python functions and classes using dependency-aware prompts.
- •For software engineering teams: Produce maintainable code documentation that follows official style guides and quality criteria automatically for large repositories.
Authors
Tingxu Han, Wei Song, Ziming Li, Yuchen Chen, Weisong Sun, Zhenpeng Chen, Chunrong Fang, Zhenyu Chen, Yang Liu
Abstract
Automatically generating high-quality documentation for software repositories remains challenging: existing approaches largely treat documentation as unconstrained text generation, lacking explicit quality specifications, depending heavily on long-context prompts over raw code, and offering limited support for reproducible evaluation. We argue that code-level documentation generation should instead be a standards-guided software engineering task, in which documentation is generated and assessed against explicit, reusable quality requirements derived from authoritative standards. We define code documentation as natural-language descriptions of repository functions and classes, organized by source-code path. We present CODEDOC, a standards-guided and dependency-aware framework that identifies dependencies between code entities via static call-graph and AST analysis and constructs dependency-aware structured prompts combining local code context, repository paths, and documentation criteria drawn from authoritative standards and style guides. We further introduce an interactive LLM-as-a-judge protocol that supplies criterion-aligned feedback to refine generated documentation along fine-grained dimensions from formal and practice-oriented standards. Experiments on ten open-source Python repositories show that CODEDOC produces higher-quality documentation than RepoAgent and a long-context baseline under standards-aligned evaluation, with relative improvements of 11.6%-17.0% and 21.4%-29.6%, respectively, while consuming roughly an order of magnitude fewer tokens per documentation entity than the long-context baseline. A human study confirms substantial alignment between LLM-based and human judgments (Spearman's rho = 0.72), and the relative findings hold across different judge LLMs. Code is available at https://github.com/ControllableModel/CodeDoc.