CAS2UML: A Handwritten Sketch-to-PlantUML Dataset for Class and Activity Diagrams

Simon Scholz; Mersedeh Sadeghi

cs.SEAug 7, 2026

CAS2UML: A Handwritten Sketch-to-PlantUML Dataset for Class and Activity Diagrams

Authors: Simon Scholz, Mersedeh Sadeghi

Organizations: University of Cologne Cologne, Germany

Abstract

Automated UML generation from sketches and images is gaining renewed attention with the rise of large language models and multimodal AI. However, reproducible evaluation remains difficult due to the lack of public datasets with executable groundtruth models. We present CAS2UML, a public dataset of 557 handdrawn UML diagrams, including 271 class diagrams and 286 activity diagrams, each paired with manually validated PlantUML code. We also provide a PlantUML-based validation tool and reusable scripts for checking the syntactic correctness and renderability of generated UML artifacts, enabling reproducible benchmarking of sketch-to-UML approaches. The dataset, validation tool, processing scripts, documentation, and demonstration video are publicly available at: Dataset: https://huggingface.co/datasets/Seym0n /cas2uml_hand-drawn_to_plantuml_dataset; Tool and Scripts: https://github.com/Seym0n/handwritten-uml-dataset; Video: https://www.youtube.com/watch?v=KQrYeGgT3hs.

Explore similar work

Query2Diagram: Answering Developer Queries with UML Diagrams
Apr 26, 2026Oleg Baryshnikov, Anton M. Alekseev, Sergey I. NikolenkoDiagrams Code Generation
Unlocking UML Class Diagram Understanding in Vision Language Models
May 12, 2026Artem Naboichenko, René PeinlDiagrams Rdf
Code2UML: Agentic LLMs with context engineering for scalable software visualization
May 23, 2026Alin-Gabriel Văduva, Anca-Ioana Andreescu, Simona-Vasilica Oprea +1Diagrams Agentic Systems

Apr 26, 2026 · cs.SEJ/K move · Enter open · S save

Query2Diagram: Answering Developer Queries with UML Diagrams

Oleg Baryshnikov, Anton M. Alekseev, Sergey I. Nikolenko

HSE University · St. Petersburg Department of Steklov Mathematical Institute, RAS, St. Petersburg State University

Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems. While automated reverse engineering tools can generate UML diagrams from code, they produce overwhelming detail without considering developer intent. We introduce query-driven UML diagram generation, where LLMs create diagrams that directly answer natural language questions about code. Unlike existing methods, our approach produces semantically focused diagrams containing only relevant elements with contextual descriptions. We fine-tune Qwen2.5-Coder-14B on a curated dataset of code files, developer queries, and corresponding diagram representations in a structured JSON format, evaluating with both automatic detection of structural defects and human assessment of semantic relevance. Results demonstrate that fine-tuning on a modest amount of manually corrected data yields dramatic improvements: our best model achieves the highest F1 scores while reducing defect rates below state-of-the-art LLMs, generating diagrams that are both structurally sound and semantically faithful to developer queries. Thus, we establish the feasibility of using LLMs for scalable contextual, on-demand documentation generation. We make our code and dataset publicly available at https://github.com/i-need-a-pencil/query2diagram.

Diagrams Code Generation Documentation Reverse Engineering

Open paper Ask about it PDF

Abstract

Explore similar work

Query2Diagram: Answering Developer Queries with UML Diagrams

Unlocking UML Class Diagram Understanding in Vision Language Models

Code2UML: Agentic LLMs with context engineering for scalable software visualization