Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs

2025-01-14

AI Summary

To address the challenges of repository comprehension and business-semantic gap in large-scale enterprise systems, this paper proposes the first repository-level hierarchical code summarization framework tailored for business applications. Methodologically, it first performs syntax-aware structural analysis via Abstract Syntax Trees (ASTs) and leverages a local large language model (LLM) to generate fine-grained function- and variable-level summaries. Subsequently, hierarchical aggregation yields file- and package-level summaries, enhanced by domain-adaptive prompting that incorporates business context—e.g., telecom Business Support Systems (BSS)—to improve interpretability and relevance. The key contribution is the first integrated modeling paradigm synergizing AST-based syntactic analysis, local LLM inference, and domain-specific prompt engineering, thereby balancing technical precision with business-intent articulation. Evaluation on real-world telecom BSS systems demonstrates a 32% increase in summary coverage and a 41% improvement in human-assessed business relevance, significantly outperforming both single-layer and general-purpose model baselines.

Technology Category

• Natural Language Processing: Summarization
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

In large-scale software development, understanding the functionality and intent behind complex codebases is critical for effective development and maintenance. While code summarization has been widely studied, existing methods primarily focus on smaller code units, such as functions, and struggle with larger code artifacts like files and packages. Additionally, current summarization models tend to emphasize low-level implementation details, often overlooking the domain and business context that are crucial for real-world applications. This paper proposes a two-step hierarchical approach for repository-level code summarization, tailored to business applications. First, smaller code units such as functions and variables are identified using syntax analysis and summarized with local LLMs. These summaries are then aggregated to generate higher-level file and package summaries. To ensure the summaries are grounded in business context, we design custom prompts that capture the intended purpose of code artifacts based on the domain and problem context of the business application. We evaluate our approach on a business support system (BSS) for the telecommunications domain, showing that syntax analysis-based hierarchical summarization improves coverage, while business-context grounding enhances the relevance of the generated summaries.

Problem

• Code Understanding
• Large Software Projects
• Business-related Code Summarization

Innovation

• Hierarchical Summarization
• Telecom Business Systems
• Two-stage Method