# IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations

arXiv: https://arxiv.org/abs/2605.13236 · HTML: https://mlsanity.com/paper/2605.13236/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 62 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 9 of 9)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [KnowGPT: Knowledge Graph based Prompting for Large Language Models](https://mlsanity.com/paper/2312.06185/) (2023)
- [LLM-assisted Graph-RAG Information Extraction from IFC Data](https://mlsanity.com/paper/2504.16813/) (2025)
- [Semantically Enriched Cross-Lingual Sentence Embeddings for Crisis-related Social Media Texts](https://mlsanity.com/paper/2403.16614/) (2024)
- [Cypher4BIM: Releasing the Power of Graph for Building Knowledge Discovery](https://mlsanity.com/paper/2405.16345/) (2024)

## Abstract (arXiv)

The Industry Foundation Classes (IFC) standard is central to building data exchange across the lifecycle, from design and construction to facility management and Digital Twin integration. In operational settings, stakeholders increasingly require access to building information without specialist knowledge of IFC's complex, deeply nested schema, motivating natural language interfaces. Existing LLM-based querying approaches typically rely on a single data representation, which is not equally suited to attribute retrieval and spatial reasoning. We present IfcLLM, a framework that combines complementary relational and graph representations, routing each query type to the more suitable backend. An LLM agent integrates both through iterative retry-and-refine reasoning, recovering from failures without user input. Evaluated across three IFC models on 30 query scenarios, our implementation achieves first-attempt accuracy between 93.3% and 100%, with all failed queries resolved via a fallback LLM. Built on an open-weight LLM, it supports local deployment in data-sensitive AEC settings.