# Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization

arXiv: https://arxiv.org/abs/2503.10737 · HTML: https://mlsanity.com/paper/2503.10737/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 41 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [CodeGemma: Open Code Models Based on Gemma](https://mlsanity.com/paper/2406.11409/) (2024)
- [Few-shot training LLMs for project-specific code-summarization](https://mlsanity.com/paper/2207.04237/) (2022)
- [Improving Automatic Source Code Summarization via Deep Reinforcement Learning](https://mlsanity.com/paper/1811.07234/) (2018)
- [Improved Code Summarization via a Graph Neural Network](https://mlsanity.com/paper/2004.02843/) (2020)
- [Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning](https://mlsanity.com/paper/2304.11384/) (2023)
- [On the Evaluation of Neural Code Summarization](https://mlsanity.com/paper/2107.07112/) (2021)
- [Automatic Code Summarization via ChatGPT: How Far Are We?](https://mlsanity.com/paper/2305.12865/) (2023)
- [Distilled GPT for Source Code Summarization](https://mlsanity.com/paper/2308.14731/) (2023)
- [Are We Building on the Rock? On the Importance of Data Preprocessing for Code Summarization](https://mlsanity.com/paper/2207.05579/) (2022)
- [Evaluating Code Summarization Techniques: A New Metric and an Empirical Characterization](https://mlsanity.com/paper/2312.15475/) (2023)
- [An Extractive-and-Abstractive Framework for Source Code Summarization](https://mlsanity.com/paper/2206.07245/) (2022)
- [A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques](https://mlsanity.com/paper/1907.10863/) (2019)
- [SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization](https://mlsanity.com/paper/2401.14727/) (2024)
- [A Prompt Learning Framework for Source Code Summarization](https://mlsanity.com/paper/2312.16066/) (2023)

## Built on by (most cited first, 3 of 3)

- [Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design](https://mlsanity.com/paper/2503.20536/) (2025)
- [Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures](https://mlsanity.com/paper/2512.05908/) (2025)
- [Prompt-Driven Code Summarization: A Systematic Literature Review](https://mlsanity.com/paper/2604.15385/) (2026)

## Abstract (arXiv)

Commenting code is a crucial activity in software development, as it aids in facilitating future maintenance and updates. To enhance the efficiency of writing comments and reduce developers' workload, researchers has proposed various automated code summarization (ACS) techniques to automatically generate comments/summaries for given code units. However, these ACS techniques primarily focus on generating summaries for code units at the method level. There is a significant lack of research on summarizing higher-level code units, such as file-level and module-level code units, despite the fact that summaries of these higher-level code units are highly useful for quickly gaining a macro-level understanding of software components and architecture. To fill this gap, in this paper, we conduct a systematic study on how to use LLMs for commenting higher-level code units, including file level and module level. These higher-level units are significantly larger than method-level ones, which poses challenges in handling long code inputs within LLM constraints and maintaining efficiency. To address these issues, we explore various summarization strategies for ACS of higher-level code units, which can be divided into three types: full code summarization, reduced code summarization, and hierarchical code summarization. The experimental results suggest that for summarizing file-level code units, using the full code is the most effective approach, with reduced code serving as a cost-efficient alternative. However, for summarizing module-level code units, hierarchical code summarization becomes the most promising strategy. In addition, inspired by the research on method-level ACS, we also investigate using the LLM as an evaluator to evaluate the quality of summaries of higher-level code units. The experimental results demonstrate that the LLM's evaluation results strongly correlate with human evaluations.