Journal of Engineering, Project, and Production Management, 2024, 14(4), 0035
Using Large Language Models for the Interpretation of Building Regulations
1Ph.D. Student, School of
Computer Science, The University of Auckland, 38 Princes Street, 1010
Auckland, New Zealand, E-mail: sffc348@aucklanduni.ac.nz
2Professor, School of Computer Science, The University of
Auckland, 38 Princes Street, 1010 Auckland, New Zealand, E-mail:
m.witbrock@auckland.ac.nz
3CEO, CAS (Codify Asset Solutions Limited), Auckland, New
Zealand, E-mail: jdimyadi@cas.net.nz; Honorary Academic, School of
Computer Science, The University of Auckland, 38 Princes Street, 1010
Auckland, New Zealand
4Professor, School of Computer Science, The University of
Auckland, 38 Princes Street, 1010 Auckland, New Zealand, E-mail: r.amor@auckland.ac.nz
(corresponding author).
Project Management
Received November 23, 2023; received revision November 12, 2024; accepted November 20, 2024
Available online November 28, 2024
Abstract: Compliance checking is an essential part of a construction project. The recent rapid uptake of building information models (BIM) in the construction industry has created more opportunities for automated compliance checking (ACC). BIM enable sharing of digital building design data that can be used to check compliance with legal requirements, which are conventionally conveyed in natural language and not intended for machine processing. Creating a computable representation of legal requirements suitable for ACC is complex, costly, and time-consuming. Large language models (LLMs) such as the generative pre-trained transformers (GPT), GPT-3.5 and GPT-4, powering OpenAI’s ChatGPT, can generate logically coherent text and source code responding to user prompts. This capability could be used to automate the conversion of building regulations into a semantic and computable representation. This paper evaluates the performance of LLMs in translating building regulations into LegalRuleML in a few-shot learning setup. By providing GPT-3.5 with only a few example translations, it can learn the basic structure of the format. Using a system prompt, we further specify the LegalRuleML representation and explore the existence of expert domain knowledge in the model. Such domain knowledge might be ingrained in GPT-3.5 through the broad pre-training but needs to be brought forth by careful contextualisation. Finally, we investigate whether strategies such as chain-of-thought reasoning and self-consistency could apply to this use case. As LLMs become more sophisticated, the increased common sense, logical coherence and means to domain adaptation can significantly support ACC, leading to more efficient and effective checking processes.
Keywords: Large language models, gpt, building codes, semantic parsing, automated compliance checking.
Copyright © Journal of Engineering, Project, and Production Management (EPPM-Journal).
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.
Requests for reprints and permissions at eppm.journal@gmail.com.
Citation: Fuchs, S., Witbrock, M., Dimyadi, J., and Amor, R. (2024). Using Large Language Models for the Interpretation of Building Regulations. A Knowledge-Driven Approach to Automate Job Hazard Analysis Process. Journal of Engineering, Project, and Production Management, 14(4), 0035.
DOI:
10.32738/JEPPM-2024-0035
Full Text
