Query2Diagram: Answering Developer Queries with UML Diagrams

2026-04-26

AI Summary

Existing automated UML tools often produce information-overloaded and semantically fragmented diagrams due to their inability to comprehend developer intent. This work proposes a query-driven approach to UML diagram generation by fine-tuning the Qwen2.5-Coder-14B model on a structured dataset comprising natural language queries, source code, and corresponding UML diagrams. To balance semantic focus with structural fidelity, the method incorporates a JSON-based intermediate representation and human-in-the-loop correction. Experimental results demonstrate that the proposed approach significantly outperforms existing large language model–based solutions in both semantic relevance and structural correctness, achieving the highest F1 score and the lowest defect rate. This study presents the first viable pathway toward on-demand generation of high-quality UML documentation.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems.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.

Problem

• software documentation
• UML diagrams
• developer queries
• reverse engineering
• code understanding

Innovation

• query-driven UML generation
• large language models
• code documentation
• semantic diagram synthesis
• fine-tuning