부산대학교 도서관

This study presents the development of a LLM-based Q&A chatbot model for interpreting complex civil engineering regulations in South Korea. Leveraging large language model capabilities, the chatbot provides accurate responses to questions concerning construction standards and specifications. Additionally, a comparative analysis function enables efficient technical reviews of in-house and on-site specifications. Compared to traditional methods, the chatbot enhances productivity and reduces human error. The research points to wider implications for industries dealing with large data and complex regulations, setting the stage for future AI applications