# LLM-based Iterative Approach to Metamodeling in Automotive

arXiv: https://arxiv.org/abs/2503.05449 · HTML: https://mlsanity.com/paper/2503.05449/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Synergy of Large Language Model and Model Driven Engineering for Automated Development of Centralized Vehicular Systems](https://mlsanity.com/paper/2404.05508/) (2024)
- [Adopting RAG for LLM-Aided Future Vehicle Design](https://mlsanity.com/paper/2411.09590/) (2024)
- [Multi-modal Summarization in Model-Based Engineering: Automotive Software Development Case Study](https://mlsanity.com/paper/2503.04506/) (2025)
- [A Model Is Not Built By A Single Prompt: LLM-Based Domain Modeling With Question Decomposition](https://mlsanity.com/paper/2410.09854/) (2024)
- [On the Utility of Domain Modeling Assistance with Large Language Models](https://mlsanity.com/paper/2410.12577/) (2024)

## Built on by (most cited first, 4 of 4)

- [Survey of GenAI for Automotive Software Development: From Requirements to Executable Code](https://mlsanity.com/paper/2507.15025/) (2025)
- [LLM-Empowered Functional Safety and Security by Design in Automotive Systems](https://mlsanity.com/paper/2601.02215/) (2026)
- [GenAI-Driven Approach to RISC-V Supply Chain Exploration](https://mlsanity.com/paper/2605.15223/) (2026)
- [LLM-Driven Approach to Modeling Tool Interoperability in Automotive Domain](https://mlsanity.com/paper/2607.14659/) (2026)

## Abstract (arXiv)

In this paper, we introduce an automated approach to domain-specific metamodel construction relying on Large Language Model (LLM). The main focus is adoption in automotive domain. As outcome, a prototype was implemented as web service using Python programming language, while OpenAI's GPT-4o was used as the underlying LLM. Based on the initial experiments, this approach successfully constructs Ecore metamodel based on set of automotive requirements and visualizes it making use of PlantUML notation, so human experts can provide feedback in order to refine the result. Finally, locally deployable solution is also considered, including the limitations and additional steps required.