Journal of Information Technology in Construction
Journal of Information Technology in Construction
ITcon Vol. 31, pg. 888-916, http://www.itcon.org/2026/38
Integrating large language models and knowledge graphs for adaptive design review
| DOI: | 10.36680/j.itcon.2026.038 | |
| submitted: | May 2026 | |
| published: | August 2026 | |
| editor(s): | Amor R | |
| authors: | Maen Alnuzha, Ph.D. candidate
Faculty of Civil and Environmental Engineering, Technion Israel Institute of Technology, Israel https://orcid.org/0009-0004-4617-2905 maen@campus.technion.ac.il Tanya Bloch, Dr The Rosalinde and Arthur Gilbert Foundation-Krengel Family Faculty Fellow, Faculty of Civil and Environmental Engineering, Technion Israel Institute of Technology, Israel https://orcid.org/0000-0002-3588-9685 bloch@technion.ac.il | |
| summary: | Automated Compliance Checking (ACC) systems are fundamentally static, unable to easily adapt to new regulations, project constraints, organizational, or practitioner-defined rules. This paper presents a framework integrating Knowledge Graphs (KGs) and Large Language Models (LLMs) to support a more extensible design review environment. In this framework, the KG acts as a structured repository for rules and executable logic, while the LLM serves as an intelligent interface. The central innovation is the human-in-the-loop feedback mechanism, where new logic generated by the LLM is validated, executed, and permanently stored in the KG, transforming it into an active, evolving validation engine. Following a Design Science Research (DSR) methodology, we implement and evaluate the framework as a prototype embedded as an Autodesk Revit add-in, demonstrating its ability to retrieve and execute existing rules from the KG, capture new requests during design, and maintain a verifiable, adaptive compliance checking system. Across a two-experiment evaluation, the system achieved 100% mapping accuracy for six existing rules, while generating new executable rules from natural language succeeded in 70% of 20 trials. Performance was strong on parameter-based checks (100%) but dropped on rules involving spatial reasoning (20–60%), where the LLM still struggles to produce reliable logic. | |
| keywords: | Automated Code Compliance (ACC), Machine Learning (ML), rule-based checking, Building Information Modeling (BIM), Knowledge Graph (KG), Large Language Models (LLMs) | |
| full text: | (PDF file, 1.408 MB) | |
| citation: | Alnuzha, M., & Bloch, T. (2026). Integrating large language models and knowledge graphs for adaptive design review. Journal of Information Technology in Construction (ITcon), 31, 888-916. https://doi.org/10.36680/j.itcon.2026.038 | |
| statistics: |