The Framework and Implementation of Using Large Language Models to Answer Questions about Building Codes and Standards
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it