LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2

TL;DR

This paper presents a novel prompt-driven method using GPT-based LLMs to facilitate semantic alignment and integration of SysML v2 models in collaborative MBSE, enhancing interoperability across organizations.

Contribution

It introduces an iterative, structured approach leveraging SysML v2 features and LLMs for semantic alignment, which is a new application in collaborative systems engineering.

Findings

Effective semantic matching demonstrated with a measurement system example.

Supports traceable, soft alignment using SysML v2 constructs.

Discusses benefits and limitations of LLM-assisted model integration.

Abstract

Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across independently developed system models. SysML v2 introduces enhanced structural modularity and formal semantics, offering a stronger foundation for interoperable modeling. Meanwhile, GPT-based Large Language Models (LLMs) provide new capabilities for assisting model understanding and integration. This paper proposes a structured, prompt-driven approach for LLM-assisted semantic alignment of SysML v2 models. The core contribution lies in the iterative development of an alignment approach and interaction prompts, incorporating model extraction, semantic matching, and verification. The approach leverages SysML v2 constructs such as alias, import, and metadata extensions to support traceable, soft alignment integration. It is demonstrated with a GPT-based LLM through an example of a measurement system. Benefits and limitations are discussed.