LLM-assisted Graph-RAG Information Extraction from IFC Data
This addresses data retrieval challenges for construction professionals, though it appears incremental as it builds on existing Graph-RAG and LLM techniques.
The researchers tackled the complexity of IFC data in construction by using LLMs with Graph-RAG to parse and retrieve building object properties and relations, enabling natural language query-response without a complex pipeline.
IFC data has become the general building information standard for collaborative work in the construction industry. However, IFC data can be very complicated because it allows for multiple ways to represent the same product information. In this research, we utilise the capabilities of LLMs to parse the IFC data with Graph Retrieval-Augmented Generation (Graph-RAG) technique to retrieve building object properties and their relations. We will show that, despite limitations due to the complex hierarchy of the IFC data, the Graph-RAG parsing enhances generative LLMs like GPT-4o with graph-based knowledge, enabling natural language query-response retrieval without the need for a complex pipeline.