EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Metadata-Grounded LLM Framework for Conversational BIM Information Retrieval in Immersive VR Environments

Muhammad Shoaib Khan, Shahzad Ahmed, Jung In Kim

Buildings · 10.08.2026 · 16 (16) · 3168

DOI: 10.3390/buildings16163168 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 10.08.2026. Verfasst von Muhammad Shoaib Khan und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Technology Innovation Program, Ministry of Trade, Industry and Energy, Korea Agency for Infrastructure Technology Advancement.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Building Information Modeling (BIM) stores rich object-level metadata, yet retrieving this information typically requires navigating complex software interfaces or formal queries, and existing BIM-VR environments rarely support conversational, semantic access to this data. Large Language Models (LLMs) offer flexible natural-language interpretation but risk generating fluent, factually incorrect responses when used without grounding, which is particularly problematic for engineering decision-making. This study develops and evaluates a metadata-grounded BIM–LLM–VR framework that enables conversational BIM information retrieval inside an immersive virtual reality environment. The framework integrates a BIM-to-Unity data exchange workflow linking VR objects to BIM metadata through stable element ID, an LLM-based interpretation module that converts natural-language queries into structured metadata filters, and a deterministic retrieval module that executes these filters against verified BIM metadata rather than allowing free-form LLM generation. A case study demonstrated five successful interaction scenarios and one negative-query validation using a multi-storey BIM model, and the framework was evaluated using a 30-query benchmark validated against ground-truth BIM metadata. The system achieved a mean precision of 99.94%, mean recall of 100.00%, and mean F1-score of 99.97%, with a mean execution time of 0.347 s. These results indicate that, under a controlled metadata schema and a predefined benchmark, the framework can translate a defined set of natural-language requests into correct element-level metadata filters inside an immersive VR environment, establishing the technical soundness of the metadata-grounding architecture.

Förderung

  • Technology Innovation Program
  • Ministry of Trade, Industry and Energy
  • Korea Agency for Infrastructure Technology Advancement
  • Ministry of Land, Infrastructure and Transport under the Smart Building R&D Program

Zitieren

APA

Khan, M. S., Ahmed, S., & Kim, J. I. (2026). A Metadata-Grounded LLM Framework for Conversational BIM Information Retrieval in Immersive VR Environments. Buildings, 16(16), 3168. https://doi.org/10.3390/buildings16163168

Vancouver

Khan MS, Ahmed S, Kim JI. A Metadata-Grounded LLM Framework for Conversational BIM Information Retrieval in Immersive VR Environments. Buildings. 2026;16(16):3168. doi:10.3390/buildings16163168

BibTeX
@article{Khan2026,
  author = {Khan, Muhammad Shoaib and Ahmed, Shahzad and Kim, Jung In},
  title = {A Metadata-Grounded LLM Framework for Conversational BIM Information Retrieval in Immersive VR Environments},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {3168},
  doi = {10.3390/buildings16163168}
}
Kostenlos starten →