paper-with-me

Papers

Large model retrieval enhancement framework for construction site risk identification

2025-08-04 · Jiawei Li, Chengye Yang, Yaochen Zhang, Weilin Sun, Lei Meng, Xiangxu Meng arxiv

This study addresses construction site hazard identification by proposing a retrieval-augmented framework that enhances large language models (LLMs) without requiring fine-tuning. Current LLM-based approaches face limitations: image-text matching struggles with complex hazards, while instruction tuning lacks generalization and is resource-intensive. Our method dynamically integrates external knowledge and retrieved similar cases via prompt tuning, overcoming LLMs' limitations in domain knowledge and feature correlation. The framework comprises a case database, an image retrieval module, and an LLM-based reasoning module. Evaluated on real-site data, our approach boosted GLM-4V's accuracy to 50%, a 35.49% improvement over baselines, with consistent gains across hazard types. Ablation studies validated the effectiveness of our image retrieval strategy, showing the superiority of our LPIPS- and CLIP-based method. The proposed technique significantly improves identification accuracy and contextual understanding, demonstrating strong generalization and offering a practical path for intelligent safety risk detection in construction.

📄 PDF Abstract BibTeX arXiv:2508.02073

Code (0)

등록된 구현이 없습니다.

Tasks

Image-text matchingImage Retrieval

Similar Papers 제목 키워드 기반

Automating construction safety inspections using a multi-modal vision-language RAG framework

2025-10-05 · Chenxin Wang, Elyas Asadi Shamsabadi, Zhaohui Chen, Luming Shen 외 arxiv

Conventional construction safety inspection methods are often inefficient as they require navigating through large volume of information. Recent advances in large vision-language models (LVLMs) provide opportunities to a…

Information Retrieval

Composite Correlation Quantization for Efficient Multimodal Retrieval

2016-05-22 · Long Mingsheng, Cao Yue, Wang Jianmin, Yu Philip S.

Efficient similarity retrieval from large-scale multimodal database is pervasive in modern search engines and social networks. To support queries across content modalities, the system should enable cross-modal correlatio…

Cross-Modal RetrievalQuantizationRetrieval

Enhancing Construction Site Safety: A Lightweight Convolutional Network for Effective Helmet Detection

2024-09-19 · Mujadded Al Rabbani Alif

In the realm of construction safety, the detection of personal protective equipment, such as helmets, plays a critical role in preventing workplace injuries. This paper details the development and evaluation of convoluti…

Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG

2026-05-07 · Jiarui Zhong, Hong Cai Chen arxiv

Retrieval-Augmented Generation (RAG) has become a core paradigm for enhancing factual grounding and multi-hop reasoning in Large Language Models (LLMs). Traditional text-based RAG often retrieves logically irrelevant pse…

Computational Efficiency

Autonomous Construction-Site Safety Inspection Using Mobile Robots: A Multilayer VLM-LLM Pipeline

2025-12-16 · Hossein Naderi, Alireza Shojaei, Philip Agee, Kereshmeh Afsari 외 arxiv

Construction safety inspection remains mostly manual, and automated approaches still rely on task-specific datasets that are hard to maintain in fast-changing construction environments due to frequent retraining. Meanwhi…