This study presents a semi-automated approach based on large-scale language models (LLMs) to address the time-consuming and error-prone nature of manual code compliance checks in Building Information Modeling (BIM). A system was developed that integrates LLMs such as GPT, Claude, Gemini, and Llama with Revit software to interpret building codes, generate Python scripts, and perform semi-automated compliance checks within a BIM environment. Case studies on single-family home projects and office building projects demonstrate the system’s ability to reduce the time and effort required for compliance checks and improve accuracy. It streamlines the identification of violations such as non-compliant room sizes, material usage, and object placement, and automatically generates actionable reports. Compared to manual methods, it eliminates repetitive tasks, simplifies complex regulations, and ensures compliance with standards. By providing a comprehensive, adaptable, and cost-effective solution, the approach proposed in this study presents a promising advancement in BIM-based compliance checks and has the potential to be applied to various regulatory documents in construction projects.
