A Hybrid Framework for Natural Language Querying of IFC Models with Relational and Graph Representations
For non-expert AEC users, this hybrid framework makes complex BIM data more accessible through natural language, though it is an incremental improvement over existing LLM-based approaches.
IfcLLM enables natural language querying of IFC-based BIM models by combining relational and graph representations with iterative LLM reasoning, achieving 93.3%-100% first-attempt accuracy on 30 query scenarios across three models.
Building Information Modeling (BIM) is widely used in the Architecture, Engineering, and Construction (AEC) industry, but the complexity of Industry Foundation Classes (IFC) limits accessibility for non-expert users. To address this, we introduce IfcLLM, a hybrid framework for natural language interaction with IFC-based BIM models. It transforms IFC models into complementary representations: a relational representation for structured element properties and geometry, and a graph representation for topological relationships. These representations are integrated through iterative retry-and-refine LLM reasoning. We implement the framework using an open-weight LLM (GPT OSS 120B), supporting reproducible and deployment-oriented workflows. Evaluation on three IFC models with queries derived from 30 scenarios shows first-attempt accuracy of 93.3%-100%, with all failures recovered using a fallback LLM. The results show that combining complementary representations with iterative reasoning enables more accessible natural language querying of IFC data while supporting routine BIM analysis tasks.