BIM Information Extraction Through LLM-based Adaptive Exploration

TL;DR

This paper introduces an adaptive exploration paradigm using LLMs to extract information from BIM models, effectively handling heterogeneity by discovering structure at runtime, and demonstrates superior performance over static methods.

Contribution

The work proposes a novel LLM-based adaptive exploration approach for BIM data extraction, addressing heterogeneity and outperforming static query methods.

Findings

Adaptive exploration significantly outperforms static query generation.

The approach effectively discovers BIM structure at runtime.

Results are validated on the open-source ifc-bench v2 benchmark.

Abstract

BIM models provide structured representations of building geometry, semantics, and topology, yet extracting specific information from them remains remarkably difficult. Current approaches translate natural language into structured queries by assuming a fixed data organization (static approach), which BIM heterogeneity eventually invalidates. We address this with a new paradigm, adaptive exploration, where an LLM-based agent iteratively executes code to extract information from a BIM model, discovering its structure at runtime instead of assuming it. We evaluate this approach on ifc-bench v2, an open-source BIM question-answering benchmark introduced alongside this work, comprising 1,027 tasks across 37 IFC models from 21 projects. A factorial ablation across two LLM capability levels and four augmentation strategies shows that adaptive exploration significantly outperforms static query generation across all configurations, regardless of the augmentation strategy. These results indicate that BIM heterogeneity is best addressed at the paradigm level, not by further optimizing static approaches.