Saved in:
Bibliographic Details
Main Authors: Lamsal, Rabindra, Zlatanova, Sisi, Xu, Haowen, Sun, Yafei, Shen, Johnson Xuesong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.13236
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914563047292928
author Lamsal, Rabindra
Zlatanova, Sisi
Xu, Haowen
Sun, Yafei
Shen, Johnson Xuesong
author_facet Lamsal, Rabindra
Zlatanova, Sisi
Xu, Haowen
Sun, Yafei
Shen, Johnson Xuesong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13236
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Hybrid Framework for Natural Language Querying of IFC Models with Relational and Graph Representations
Lamsal, Rabindra
Zlatanova, Sisi
Xu, Haowen
Sun, Yafei
Shen, Johnson Xuesong
Computation and Language
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.
title A Hybrid Framework for Natural Language Querying of IFC Models with Relational and Graph Representations
topic Computation and Language
url https://arxiv.org/abs/2605.13236