Using Large Language Models to Identify Project Risks for Sustainable Operations

Risk identification in construction projects is crucial for sustainable operations. However, it is often hindered by omissions and participant subjectivity. This study explores the application of large language models (LLMs) in identifying risks and impacted activities within construction projects. The methodology includes developing a RiskGPT agent, fine-tuning it with prompt words, augmenting it with structural knowledge, and evaluating its application on real projects. Preliminary results from a case study demonstrate the potential benefits and challenges of using LLMs in this context. Despite the generalization tendency and occasional technical issues, LLMs show promise in augmenting human expertise and providing a robust foundation for risk management in construction projects. Future research should focus on improving training data quality, enhancing contextual understanding, and refining the integration of LLM outputs with human insights to maximize their practical applicability.