DocFetch - Towards Generating Software Documentation from Multiple Software Artifacts

• URL: http://arxiv.org/abs/2508.17719v1
• Date: Mon, 25 Aug 2025 06:54:27 GMT
• Title: DocFetch - Towards Generating Software Documentation from Multiple Software Artifacts
• Authors: Akhila Sri Manasa Venigalla, Sridhar Chimalakonda,
• Abstract summary: Existing automated approaches to generate documentation largely focus on source code.<n>We propose DocFetch, to generate different types of documentation from multiple software artifacts.<n>We evaluate the performance of DocFetch using a manually curated groundtruth dataset.
• Score: 5.780991619197141
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Software Documentation plays a major role in the usage and development of a project. Widespread adoption of open source software projects contributes to larger and faster development of the projects, making it difficult to maintain the associated documentation. Existing automated approaches to generate documentation largely focus on source code. However, information useful for documentation is observed to be scattered across various artifacts that co-evolve with the source code. Leveraging this information across multiple artifacts can reduce the effort involved in maintaining documentation. Hence, we propose DocFetch, to generate different types of documentation from multiple software artifacts. We employ a multi-layer prompt based LLM and generate structured documentation corresponding to different documentation types for the data consolidated in DocMine dataset. We evaluate the performance of DocFetch using a manually curated groundtruth dataset by analysing the artifacts in DocMine. The evaluation yields a highest BLEU-4 score of 43.24% and ROUGE-L score of 0.39 for generation of api-related and file-related information from five documentation sources. The generation of other documentation type related information also reported BLEU-4 scores close to 30% indicating good performance of the approach. Thus,DocFetch can be employed to semi-automatically generate documentation, and helps in comprehending the projects with minimal effort in maintaining the documentation.

Related papers

• Docopilot: Improving Multimodal Models for Document-Level Understanding [87.60020625241178]
  We present a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents.<n>This dataset includes diverse document structures, extensive cross-page dependencies, and real question-answer pairs derived from the original documents.<n>Building on the dataset, we develop a native multimodal model, Docopilot, which can accurately handle document-level dependencies without relying on RAG.
  arXiv  Detail & Related papers  (2025-07-19T16:03:34Z)
• OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations [22.336858733121158]
  We introduce OmniDocBench, a novel benchmark featuring high-quality annotations across nine document sources.<n>We conduct a thorough evaluation of both pipeline-based methods and end-to-end vision-language models.
  arXiv  Detail & Related papers  (2024-12-10T16:05:56Z)
• BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks [57.589795399265945]
  We introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks.<n>We also introduce BigDocs-Bench, a benchmark suite with 10 novel tasks.<n>Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o.
  arXiv  Detail & Related papers  (2024-12-05T21:41:20Z)
• Supporting Software Maintenance with Dynamically Generated Document Hierarchies [41.407915858583344]
  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.
  arXiv  Detail & Related papers  (2024-08-11T17:11:14Z)
• 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)
• Understanding Documentation Use Through Log Analysis: An Exploratory Case Study of Four Cloud Services [14.104545948572836]
  We analyze documentation page-view logs from four cloud-based industrial services. By analyzing page-view logs for over 100,000 users, we find diverse patterns of documentation page visits. We propose documentation page-view log analysis as a feasible technique for design audits of documentation.
  arXiv  Detail & Related papers  (2023-10-16T20:37:29Z)
• DocumentNet: Bridging the Data Gap in Document Pre-Training [78.01647768018485]
  We propose a method to collect massive-scale and weakly labeled data from the web to benefit the training of VDER models. The collected dataset, named DocumentNet, does not depend on specific document types or entity sets. Experiments on a set of broadly adopted VDER tasks show significant improvements when DocumentNet is incorporated into the pre-training.
  arXiv  Detail & Related papers  (2023-06-15T08:21:15Z)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)
• DocBank: A Benchmark Dataset for Document Layout Analysis [114.81155155508083]
  We present textbfDocBank, a benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents.
  arXiv  Detail & Related papers  (2020-06-01T16:04:30Z)

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.