Class Model Generation from Requirements using Large Language Models

2026-03-09

AI Summary

This work proposes an automated approach leveraging large language models (LLMs) to generate UML class diagrams from natural language requirements, aiming to reduce manual effort in software design. The method employs chain-of-thought prompting to extract domain entities, attributes, and relationships, followed by structured diagram generation using PlantUML. A novel dual-validation framework is introduced: one component utilizes LLMs such as Grok and Mistral as judges for automated quality assessment, while the other incorporates expert human evaluation. Experimental results demonstrate that the generated class diagrams achieve high performance across five dimensions—including completeness and correctness—and show strong alignment between LLM-based evaluations and expert judgments, thereby confirming the feasibility and reliability of LLMs in both automated modeling and quality assessment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Knowledge Representation and Reasoning: Description Logics

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• 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

Abstract

The emergence of Large Language Models (LLMs) has opened new opportunities to automate software engineering activities that traditionally require substantial manual effort. Among these, class diagram generation represents a critical yet resource-intensive phase in software design. This paper investigates the capabilities of state-of-the-art LLMs, including GPT-5, Claude Sonnet 4.0, Gemini 2.5 Flash Thinking, and Llama-3.1-8B-Instruct, to generate UML class diagrams from natural language requirements automatically. To evaluate the effectiveness and reliability of LLM-based model generation, we propose a comprehensive dual-validation framework that integrates an LLM-as-a-Judge methodology with human-in-the-loop assessment. Using eight heterogeneous datasets, we apply chain-of-thought prompting to extract domain entities, attributes, and associations, generating corresponding PlantUML representations. The resulting models are evaluated across five quality dimensions: completeness, correctness, conformance to standards, comprehensibility, and terminological alignment. Two independent LLM judges (Grok and Mistral) perform structured pairwise comparisons, and their judgments are further validated against expert evaluations. Our results demonstrate that LLMs can generate structurally coherent and semantically meaningful UML diagrams, achieving substantial alignment with human evaluators. The consistency observed between LLM-based and human-based assessments highlights the potential of LLMs not only as modeling assistants but also as reliable evaluators in automated requirements engineering workflows, offering practical insights into the capabilities and limitations of LLM-driven UML class diagram automation.

Problem

• Class Diagram Generation
• Natural Language Requirements
• UML
• Software Design Automation
• Large Language Models

Innovation

• Large Language Models
• UML Class Diagram Generation
• LLM-as-a-Judge
• Chain-of-Thought Prompting
• Automated Requirements Engineering