# Behavioral Augmentation of UML Class Diagrams: An Empirical Study of Large Language Models for Method Generation

arXiv: https://arxiv.org/abs/2506.00788 · HTML: https://mlsanity.com/paper/2506.00788/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [Recommending Metamodel Concepts during Modeling Activities with Pre-Trained Language Models](https://mlsanity.com/paper/2104.01642/) (2021)
- [Programming with AI: Evaluating ChatGPT, Gemini, AlphaCode, and GitHub Copilot for Programmers](https://mlsanity.com/paper/2411.09224/) (2024)

## Built on by (most cited first, 1 of 1)

- [MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation](https://mlsanity.com/paper/2511.14967/) (2025)

## Abstract (arXiv)

Automating the enrichment of UML class diagrams with behavioral methods from natural language use cases is a significant challenge. This study evaluates nine large language models (LLMs) in augmenting a methodless UML diagram (21 classes, 17 relationships) using 21 structured waste-management use cases. A total of 90 diagrams (3,373 methods) were assessed across six metrics: method quantity, signature richness (visibility, names, parameters, return types), annotation completeness (linking to use cases/actions), structural fidelity, syntactic correctness (PlantUML compilation), and naming convergence (across models). All LLMs produced valid PlantUML diagrams adhering to UML conventions. Some models excelled in method coverage and annotation accuracy, while others showed richer parameterization but weaker traceability. These results demonstrate that LLMs can generate well-structured methods with consistent naming, advancing automated behavioral modeling. However, inconsistencies in annotations and signatures highlight the need for improved prompt engineering and model selection. The rapid generation of these methods supports Agile practices by enabling faster design iterations. Despite their capabilities, human oversight is essential to ensure accuracy, appropriateness, and semantic alignment. This positions LLMs as collaborative partners in software design. All experimental artifacts (texttt.puml, texttt.png, texttt.csv) are publicly available for reproducibility.