# Model Generation with LLMs: From Requirements to UML Sequence Diagrams

arXiv: https://arxiv.org/abs/2404.06371 · HTML: https://mlsanity.com/paper/2404.06371/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 9 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design](https://mlsanity.com/paper/2303.07839/) (2023)
- [Advancing Requirements Engineering through Generative AI: Assessing the Role of LLMs](https://mlsanity.com/paper/2310.13976/) (2023)
- [Investigating ChatGPT's Potential to Assist in Requirements Elicitation Processes](https://mlsanity.com/paper/2307.07381/) (2023)
- [Prompts Matter: Insights and Strategies for Prompt Engineering in Automated Software Traceability](https://mlsanity.com/paper/2308.00229/) (2023)
- [Requirements Engineering using Generative AI: Prompts and Prompting Patterns](https://mlsanity.com/paper/2311.03832/) (2023)
- [Automatic Transformation of Natural to Unified Modeling Language: A Systematic Review](https://mlsanity.com/paper/2204.00932/) (2022)

## Built on by (most cited first, 11 of 11)

- [Accurate and Consistent Graph Model Generation from Text with Large Language Models](https://mlsanity.com/paper/2508.00255/) (2025)
- [MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation](https://mlsanity.com/paper/2511.14967/) (2025)
- [Assessing LLMs for Front-end Software Architecture Knowledge](https://mlsanity.com/paper/2502.19518/) (2025)
- [NOMAD: A Multi-Agent LLM System for UML Class Diagram Generation from Natural Language Requirements](https://mlsanity.com/paper/2511.22409/) (2025)
- [EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering](https://mlsanity.com/paper/2605.27332/) (2026)
- [Data Dependency-Aware Code Generation from Enhanced UML Sequence Diagrams](https://mlsanity.com/paper/2508.03379/) (2025)
- [AI for Requirements Engineering: Industry adoption and Practitioner perspectives](https://mlsanity.com/paper/2511.01324/) (2025)
- [The Software Engineering Simulations Lab: Agentic AI for RE Quality Simulations](https://mlsanity.com/paper/2511.17762/) (2025)
- [Instruction-Tuning Open-Weight Language Models for BPMN Model Generation](https://mlsanity.com/paper/2512.12063/) (2025)
- [LLM-based Automated Architecture View Generation: Where Are We Now?](https://mlsanity.com/paper/2603.21178/) (2026)
- [Query2Diagram: Answering Developer Queries with UML Diagrams](https://mlsanity.com/paper/2604.23816/) (2026)

## Abstract (arXiv)

Complementing natural language (NL) requirements with graphical models can improve stakeholders' communication and provide directions for system design. However, creating models from requirements involves manual effort. The advent of generative large language models (LLMs), ChatGPT being a notable example, offers promising avenues for automated assistance in model generation. This paper investigates the capability of ChatGPT to generate a specific type of model, i.e., UML sequence diagrams, from NL requirements. We conduct a qualitative study in which we examine the sequence diagrams generated by ChatGPT for 28 requirements documents of various types and from different domains. Observations from the analysis of the generated diagrams have systematically been captured through evaluation logs, and categorized through thematic analysis. Our results indicate that, although the models generally conform to the standard and exhibit a reasonable level of understandability, their completeness and correctness with respect to the specified requirements often present challenges. This issue is particularly pronounced in the presence of requirements smells, such as ambiguity and inconsistency. The insights derived from this study can influence the practical utilization of LLMs in the RE process, and open the door to novel RE-specific prompting strategies targeting effective model generation.