Automated Semantic Fault Localization in SysML v2: A Human-in-the-Loop Framework Using Knowledge-Graph Augmented LLMs

The paper introduces a human-in-the-loop framework for automated semantic fault localization in SysML v2, integrating a fine-tuned Small Language Model (SLM) with a domain knowledge graph to identify and repair semantic errors that syntactically valid but violate domain rules. Specifically, the framework utilizes two models, Qwen2.5-Coder-1.5B and DeepSeek-Coder-6.7B, achieving a significant improvement in fault repair effectiveness from under 3% to over 91% on 1,184 test samples, while also reducing output token length by over 60%. This approach enhances model-based systems engineering (MBSE) tools by providing AI-assisted verification capabilities that maintain human oversight in the design process.