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

arXiv: https://arxiv.org/abs/2501.07857 · HTML: https://mlsanity.com/paper/2501.07857/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 14 Jan 2025.

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [A Transformer-based Approach for Source Code Summarization](https://mlsanity.com/paper/2005.00653/) (2020)
- [AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology](https://mlsanity.com/paper/2406.11912/) (2024)
- [A Deep Dive into Large Language Models for Automated Bug Localization and Repair](https://mlsanity.com/paper/2404.11595/) (2024)
- [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024)
- [CommitBERT: Commit Message Generation Using Pre-Trained Programming Language Model](https://mlsanity.com/paper/2105.14242/) (2021)
- [Developer-Intent Driven Code Comment Generation](https://mlsanity.com/paper/2302.07055/) (2023)
- [Automated Commit Message Generation with Large Language Models: An Empirical Study and Beyond](https://mlsanity.com/paper/2404.14824/) (2024)

## Built on by (most cited first, 6 of 6)

- [Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants](https://mlsanity.com/paper/2601.10112/) (2026)
- [Evaluating Repository-level Software Documentation via Question Answering and Feature-Driven Development](https://mlsanity.com/paper/2604.06793/) (2026)
- [Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases](https://mlsanity.com/paper/2607.01425/) (2026)
- [Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures](https://mlsanity.com/paper/2512.05908/) (2025)
- [Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents](https://mlsanity.com/paper/2605.18684/) (2026)
- [Prompt-Driven Code Summarization: A Systematic Literature Review](https://mlsanity.com/paper/2604.15385/) (2026)

## Abstract (arXiv)

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.