Empirical Validation of wise‑BIM: A Large‑Language‑Model- Driven Framework for BIM Modeling Evaluation and Feedback

Do Young Kim; Sun Joo Cho

doi:10.13161/kibim.2025.15.3.057

All Issue

2025 Vol.15, Issue 3 Preview Page Next Page

Research Article

Empirical Validation of wise‑BIM: A Large‑Language‑Model- Driven Framework for BIM Modeling Evaluation and Feedback LLM 기반 BIM 모델링 평가 및 피드백 프레임워크의 설계와 실증적 효과

30 September 2025. pp. 57-64

PDF XML

Abstract

This study proposes wise-BIM, a BIM modeling evaluation and feedback framework that embeds large language models (LLMs), and empirically validates its effectiveness in civil-engineering design and checking scenarios. The framework comprises three stages: (A) structuring decision nodes, (B) defining purpose-centered elements, and (C) a RAG-prompt conversational feedback loop. By integrating static resources with dynamic reasoning, wise-BIM provides contextualized guidance to modelers without training on project files. In a minimum-viable expert study across representative tasks, the LLM-RAG condition, compared with manual work, improved goal refinement, reduced error-detection time, decreased rework cycles, lowered cognitive workload (NASA-TLX), reduced clarification requests (Clarify count), and increased usability (SUS). We also observed model-specific trade-offs between communication efficiency and the depth of goal elaboration, informing practical model-selection strategies. These findings indicate that conversational feedback by LLMs can mitigate the adaptability and explainability limitations of rule-based automation in BIM and provide a human-in-the-loop pathway for quality control during modeling.

Keywords

BIM

Large Language Model (LLM)

Retrieval‑Augmented Generation (RAG)

Decision Support

Error Detection

NASA‑TLX

System Usability Scale (SUS)

Civil Infrastructure

키워드

BIM

대규모 언어 모델 (LLM)

검색 기반 생성 (RAG)

의사결정 지원

오류 탐지

NASA‑TLX

시스템 사용성 척도 (SUS)

토목 인프라

References

Adebiyi, A., Ajenifuja, O., Zhang, X. (2024). Digital Twins and Civil Engineering Phases: Reorienting Adoption Strategies, Automation in Construction, 24(10), Article 100801. arXiv:2403.02426.

10.1115/1.4066181

Eastman, C., Lee, J., Jeong, Y., Lee, J. (2009). Automatic Rule- Based Checking of Building Designs, Automation in Construction, 18(8), pp. 1011–1033.

10.1016/j.autcon.2009.07.002

Fuchs, S., Witbrock, M., Dimyadi, J., Amor, R. (2024). Using Large Language Models for the Interpretation of Building Regulations. arXiv preprint, arXiv:2407.21060. https://doi.org/10.48550/arXiv.2407.21060.

10.48550/arXiv.2407.21060

Hellin, S., Nousias, S., Borrmann, A. (2025). Natural Language Information Retrieval from BIM Models: An LLM-Based Agentic Workflow Approach, In Proc. European Conference on Computing in Construction, pp. 1–8.

Kim, H., Anderson, K., Lee, S., Hildreth, J. (2013). Generating Construction Schedules through Automatic Data Extraction using Open BIM Technology, Automation in Construction, 35, pp. 285–295.

10.1016/j.autcon.2013.05.020

Koo, B., Shin, B. (2018). Applying Novelty Detection to Identify Model Element to IFC Class Misclassifications on Architectural and Infrastructure Building Information Models, Journal of Computational Design and Engineering, 5(4), pp. 391–400.

10.1016/j.jcde.2018.03.002

Koo, B., Shin, B., Krijnen, T. F. (2017). Employing Outlier and Novelty Detection for Checking the Integrity of BIM to IFC Entity Associations, Proceedings of the 34th International Symposium on Automation and Robotics in Construction, pp. 6-13.

10.22260/ISARC2017/0002

Liu, B., Chen, H. (2025). BIMCoder: A Comprehensive Large Language Model Fusion Framework for Natural Language- Based BIM Information Retrieval, Applied Sciences, 15(14), 7647. https://doi.org/10.3390/app15147647.

10.3390/app15147647

Madireddy, S., Gao, L., Din, Z. U., Kim, K., Senouci, A., Han, Z., Zhang, Y. (2025). Large Language Model-Driven Code Compliance Checking in Building Information Modeling, Electronics, 14(11), 2146. https://doi.org/10.3390/electronics14112146.

10.3390/electronics14112146

Santiago, N., Cuperschmid, R. (2023). Technological Challenges of BIM-Based Automatic Rule Checking: A Review, Information Technology in Construction, 16(5), pp. 392-414.

Information

Publisher :Journal of KIBIM
Publisher(Ko) :한국BIM학회
Journal Title :Journal of KIBIM
Journal Title(Ko) :한국BIM학회논문집
Volume : 15
No :3
Pages :57-64
Received Date : 2025-08-04; 2025-09-01
Accepted Date : 2025-09-01
DOI :https://doi.org/10.13161/kibim.2025.15.3.057

Journal of KIBIM ISSN:2288-1697(Print) 2288-1697(Online) 한국BIM학회논문집

All Issue