Code-Craft: Hierarchical Graph-Based Code Summarization for Enhanced Context Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910909674291200 |
|---|---|
| author | Sounthiraraj, David Hancock, Jared Kortam, Yassin Javvaji, Ashok Singh, Prabhat Shankar, Shaila |
| author_facet | Sounthiraraj, David Hancock, Jared Kortam, Yassin Javvaji, Ashok Singh, Prabhat Shankar, Shaila |
| contents | Understanding and navigating large-scale codebases remains a significant challenge in software engineering. Existing methods often treat code as flat text or focus primarily on local structural relationships, limiting their ability to provide holistic, context-aware information retrieval. We present Hierarchical Code Graph Summarization (HCGS), a novel approach that constructs a multi-layered representation of a codebase by generating structured summaries in a bottom-up fashion from a code graph. HCGS leverages the Language Server Protocol for language-agnostic code analysis and employs a parallel level-based algorithm for efficient summary generation. Through extensive evaluation on five diverse codebases totaling 7,531 functions, HCGS demonstrates significant improvements in code retrieval accuracy, achieving up to 82 percentage relative improvement in top-1 retrieval precision for large codebases like libsignal (27.15 percentage points), and perfect Pass@3 scores for smaller repositories. The system's hierarchical approach consistently outperforms traditional code-only retrieval across all metrics, with particularly substantial gains in larger, more complex codebases where understanding function relationships is crucial. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08975 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Code-Craft: Hierarchical Graph-Based Code Summarization for Enhanced Context Retrieval Sounthiraraj, David Hancock, Jared Kortam, Yassin Javvaji, Ashok Singh, Prabhat Shankar, Shaila Software Engineering Information Retrieval Understanding and navigating large-scale codebases remains a significant challenge in software engineering. Existing methods often treat code as flat text or focus primarily on local structural relationships, limiting their ability to provide holistic, context-aware information retrieval. We present Hierarchical Code Graph Summarization (HCGS), a novel approach that constructs a multi-layered representation of a codebase by generating structured summaries in a bottom-up fashion from a code graph. HCGS leverages the Language Server Protocol for language-agnostic code analysis and employs a parallel level-based algorithm for efficient summary generation. Through extensive evaluation on five diverse codebases totaling 7,531 functions, HCGS demonstrates significant improvements in code retrieval accuracy, achieving up to 82 percentage relative improvement in top-1 retrieval precision for large codebases like libsignal (27.15 percentage points), and perfect Pass@3 scores for smaller repositories. The system's hierarchical approach consistently outperforms traditional code-only retrieval across all metrics, with particularly substantial gains in larger, more complex codebases where understanding function relationships is crucial. |
| title | Code-Craft: Hierarchical Graph-Based Code Summarization for Enhanced Context Retrieval |
| topic | Software Engineering Information Retrieval |
| url | https://arxiv.org/abs/2504.08975 |