The Framework and Implementation of Using Large Language Models to Answer Questions about Building Codes and Standards
Isaac Joffe, George Felobes, Youssef Elgouhari, Mohammad Talebi Kalaleh, Qipei Mei, Ying Hei Chui
Abstract
Civil and structural engineering design projects are subject to strict regulations of relevant codes and standards to guarantee that certain standards of safety, reliability, and efficiency are met. However, ensuring that all engineering designs comply with the precise provisions of pertinent civil and structural engineering codes and standards is a complex and time-consuming task currently completed by professional engineers. Recent advancements in artificial intelligence have enabled large language models (LLMs) to complete abstract and complex tasks, such as answering questions based on provided context and summarizing text passages, with high accuracy. This work presents a novel framework to build an open-source and scalable LLM-based application allowing engineers to quickly receive accurate answers to their codes-and-standards-related questions alongside corresponding citations simply by interacting in natural language with a ChatGPT-style chatbot. This work also presents a preliminary implementation of this framework using the National Building Code of Canada 2020. The system implemented achieves promising results, indicating that the proposed framework may be a useful tool to assist design engineers in efficiently and effectively completing their work and that this approach holds promise for applications to other domains.