SEMar 10

Class Model Generation from Requirements using Large Language Models

arXiv:2603.09100v119.7h-index: 4
Predicted impact top 64% in SE · last 90 daysOriginality Synthesis-oriented
AI Analysis

This addresses the resource-intensive task of class diagram generation in software design for software engineers, though it appears incremental as it applies existing LLMs to a new domain.

This paper investigates using state-of-the-art LLMs (GPT-5, Claude Sonnet 4.0, Gemini 2.5 Flash Thinking, Llama-3.1-8B-Instruct) to automatically generate UML class diagrams from natural language requirements, achieving substantial alignment with human evaluators through a dual-validation framework.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes