Supporting Software Maintenance with Dynamically Generated Document Hierarchies

• URL: http://arxiv.org/abs/2408.05829v1
• Date: Sun, 11 Aug 2024 17:11:14 GMT
• Title: Supporting Software Maintenance with Dynamically Generated Document Hierarchies
• Authors: Katherine R. Dearstyne, Alberto D. Rodriguez, Jane Cleland-Huang,
• Abstract summary: We present HGEN, a fully automated pipeline that transforms source code through a series of six stages into a well-organized hierarchy of formatted documents. We evaluate HGEN both quantitatively and qualitatively. Results show that HGEN produces artifact hierarchies similar in quality to manually constructed documentation, with much higher coverage of the core concepts than the baseline approach.
• Score: 41.407915858583344
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Software documentation supports a broad set of software maintenance tasks; however, creating and maintaining high-quality, multi-level software documentation can be incredibly time-consuming and therefore many code bases suffer from a lack of adequate documentation. We address this problem through presenting HGEN, a fully automated pipeline that leverages LLMs to transform source code through a series of six stages into a well-organized hierarchy of formatted documents. We evaluate HGEN both quantitatively and qualitatively. First, we use it to generate documentation for three diverse projects, and engage key developers in comparing the quality of the generated documentation against their own previously produced manually-crafted documentation. We then pilot HGEN in nine different industrial projects using diverse datasets provided by each project. We collect feedback from project stakeholders, and analyze it using an inductive approach to identify recurring themes. Results show that HGEN produces artifact hierarchies similar in quality to manually constructed documentation, with much higher coverage of the core concepts than the baseline approach. Stakeholder feedback highlights HGEN's commercial impact potential as a tool for accelerating code comprehension and maintenance tasks. Results and associated supplemental materials can be found at https://zenodo.org/records/11403244

Related papers

• Linking Code and Documentation Churn: Preliminary Analysis [2.033674689332928]
  This study investigates the synchrony between code churn and documentation updates in three GitHub open-source projects. Preliminary results indicate varying degrees of synchrony across projects, highlighting the importance of integrated concurrent documentation practices. The novelty of this study lies in demonstrating how synchronizing code changes with documentation updates can improve the development lifecycle by enhancing diversity and efficiency.
  arXiv  Detail & Related papers  (2024-10-08T12:41:58Z)
• HDT: Hierarchical Document Transformer [70.2271469410557]
  HDT exploits document structure by introducing auxiliary anchor tokens and redesigning the attention mechanism into a sparse multi-level hierarchy. We develop a novel sparse attention kernel that considers the hierarchical structure of documents.
  arXiv  Detail & Related papers  (2024-07-11T09:28:04Z)
• DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models [63.466265039007816]
  We present DocGenome, a structured document benchmark constructed by annotating 500K scientific documents from 153 disciplines in the arXiv open-access community. We conduct extensive experiments to demonstrate the advantages of DocGenome and objectively evaluate the performance of large models on our benchmark.
  arXiv  Detail & Related papers  (2024-06-17T15:13:52Z)
• Automated User Story Generation with Test Case Specification Using Large Language Model [0.0]
  We developed a tool "GeneUS" to automatically create user stories from requirements documents. The output is provided in format leaving the possibilities open for downstream integration to the popular project management tools.
  arXiv  Detail & Related papers  (2024-04-02T01:45:57Z)
• RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation [79.83270415843857]
  We introduce RepoAgent, a large language model powered open-source framework aimed at proactively generating, maintaining, and updating code documentation. We have validated the effectiveness of our approach, showing that RepoAgent excels in generating high-quality repository-level documentation.
  arXiv  Detail & Related papers  (2024-02-26T15:39:52Z)
• On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval [59.25292920967197]
  Few-shot document entity retrieval (VDER) is an important topic in industrial NLP applications. FewVEX is a new dataset to boost future research in the field of entity-level few-shot VDER. We present a task-aware meta-learning based framework, with a central focus on achieving effective task personalization.
  arXiv  Detail & Related papers  (2023-11-01T17:51:43Z)
• A Study of Documentation for Software Architecture [7.011803832284996]
  We asked 65 participants to answer software architecture understanding questions. Answers to questions that require applying and creating activities were statistically significantly associated with the use of the system's source code. We conclude that, in the limited experimental context studied, our results contradict the hypothesis that the format of architectural documentation matters.
  arXiv  Detail & Related papers  (2023-05-26T22:14:53Z)
• HADES: Homologous Automated Document Exploration and Summarization [3.3509104620016092]
  HADES is designed to streamline the work of professionals dealing with large volumes of documents. The tool employs a multi-step pipeline that begins with processing PDF documents using topic modeling, summarization, and analysis of the most important words for each topic.
  arXiv  Detail & Related papers  (2023-02-25T15:16:10Z)
• Generate rather than Retrieve: Large Language Models are Strong Context Generators [74.87021992611672]
  We present a novel perspective for solving knowledge-intensive tasks by replacing document retrievers with large language model generators. We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
  arXiv  Detail & Related papers  (2022-09-21T01:30:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.