@inproceedings{73d8c26a09ab4fcea298c92e6b03e13a,
title = "ENHANCING VISUAL-LLM THROUGH PROMPT ENGINEERING AND HYBRID RETRIEVAL-AUGMENTED GENERATION FOR SITE SAFETY COMPLIANCE CHECKING",
abstract = "The increasing prevalence of safety incidents on construction sites states the urgent need for enhanced monitoring. This study proposes an innovative hybrid Retrieval-Augmented Generation (RAG) algorithm to compliance check accuracy for site images. By integrating the Visual Language Model (VLM), we developed an algorithm capable of mastering domain knowledge without fine-tuning and addressing the limitation of interpreting RAG technology with visual information. A three-phased prompting framework was designed to enhance the VLM's compliance analysis abilities. Experiments based on actual construction site in Hong Kong demonstrated 21.98\% increase in retrieval accuracy.",
keywords = "Construction Site Safety, Image-based Monitoring, Multimodal Large Language Models, Retrieval-Augmented Generation (RAG)",
author = "Guo, \{Koi Xiaowen\} and Wong, \{Peter Kok Yiu\} and Cheng, \{Jack C.P.\} and Xingyu Tao and Leung, \{Pak Him\}",
note = "Publisher Copyright: {\textcopyright} 2025, European Council on Computing in Construction (EC3). All rights reserved.; European Conference on Computing in Construction, EC3 2025 and 42nd International CIB W78 Conference on IT in Construction, 2025 ; Conference date: 14-07-2025 Through 17-07-2025",
year = "2025",
month = jul,
doi = "10.35490/EC3.2025.221",
language = "English",
isbn = "9789083451312",
series = "Proceedings of the European Conference on Computing in Construction",
publisher = "European Council on Computing in Construction (EC3)",
editor = "Ekaterina Petrova and Marijana Sre{\'c}kovi{\'c} and Pedro Meda and Soman, \{Ranjith K.\} and Daniel Hall and Jakob Beetz and Jenn McArthur",
booktitle = "Proceedings of the 2025 European Conference on Computing in Construction and 42nd International CIB W78 Conference on Information Technology in Construction, 2025",
}