The highway construction industry carries substantial safety risks for workers, necessitating thorough accident analyses to implement effective preventive measures. Current research lacks comprehensive investigations into safety incidents, relying heavily on conventional statistical methods and overlooking valuable textual information in publicly available databases. This study leverages a state-of-the-art large language model (LLM), specifically OpenAI’s GPT-3.5 model. The primary focus is to enhance text-based incident analysis that is sourced from OSHA’s Severe Injury Reports (SIR) database. By incorporating novel natural language processing (NLP) techniques, dimensionality reduction, clustering algorithms, and LLM prompting of incident narratives, the study aims to develop an approach to the analysis of major accident causes in highway construction. The resulting cluster analysis, coupled with LLM summarization and cause identification, reveals the major accident types, such as heat-related and struck-by injuries, as well as commonalities between incidents. This research showcases the potential of artificial intelligence (AI) and LLM technology in data-driven analysis. By efficiently processing textual data and providing insightful analysis, the study fosters practical implications for safety professionals and the development of more effective accident prevention and intervention strategies within the industry.

State Departments of Transportation (DOTs) are facing workforce shortages and a decline in experienced construction workers. One approach to address this problem is through the active adoption of modern technologies, particularly artificial intelligence (AI) tools. Multimodal large language models (LLMs) offer emerging capabilities, such as instruction following and question answering, making them suitable for numerous practical applications in civil engineering. A key area of interest is effectively communicating complex concepts to train engineers and construction workers; however, there remains a need for a structured approach to selecting appropriate models and evaluating LLMs’ knowledge for specialized engineering areas. This paper presents an evaluation of twenty-six different LLMs using over 100 automatically generated questions, revealing a wide range of accuracies in concrete pavement construction expertise. The proposed methodology uses carefully selected, domain-specific documents and best practices to automatically build a customized framework for assessing model performance in niche fields. It also demonstrates that techniques like the “Retry” method and the integration of domain-specific information through retrieval augmented generation (RAG) can significantly enhance LLM accuracy. The results indicate that open-source, small- and medium-sized models combined with RAG, which can run efficiently on laptop computers, could be deployed for future applications. These techniques show promise for model improvement without additional fine-tuning or retraining, significantly reducing the computational requirements for tailored engineering tasks.

Recent advancements in generative artificial intelligence (GenAI), particularly large language models (LLMs), have shown promise in enhancing safety analysis within the construction industry. This study explores the integration of structured information from the U.S. Pennsylvania Department of Transportation’s job safety analysis (JSA) documents with unstructured accident narratives from the U.S. Occupational Safety and Health Administration’s Integrated Management Information System (IMIS), focusing on asphalt pavement construction—a sector marked by complex operations and hazardous equipment. Multiple LLMs were employed to classify accident narratives across four dimensions: construction type, relevant JSA job and step, environmental or operational influence, and hazard type. This approach aims to identify frequently cited work activities, assess gaps in safety documentation, and improve future hazard recognition. While general job classification achieved moderate success, performance declined for step-level and contextual classifications, largely because of ambiguous language and overlapping job responsibilities in the narratives. Despite these limitations, LLMs uncovered critical patterns. Paver and roller operations emerged as high-risk activities, often influenced by environmental factors such as traffic or weather. Furthermore, exploratory hazard analysis revealed that model-suggested hazard labels were sometimes more contextually appropriate than those in the original IMIS database, indicating opportunities for data refinement. By aligning structured safety documentation with real-world incidents through GenAI, this study highlights a novel pathway for data-driven safety planning in highway construction. While expert oversight remains essential, the results demonstrate the potential of LLMs to support more adaptive, targeted, and proactive approaches to risk assessment and mitigation.

The construction industry remains among the most hazardous, with workers in horizontal transportation infrastructure facing additional risks from dynamic work zones, live traffic exposure, and variable environmental conditions. Immersive technologies such as Virtual Reality (VR) and Augmented Reality (AR) offer new approaches to accident analysis and prevention, yet their applications toward improving occupational safety in transportation construction have not been comprehensively reviewed. This paper presents a systematic review of 54 studies published between 2016 and 2025 collected from two online databases (Transportation Research International Documentation and Web of Science). This review synthesizes how immersive technologies contribute to occupational risk assessment, safety training, and real-time hazard monitoring in the construction of roads, bridges, tunnels, and work zones. Each study is classified across two dimensions: the immersive medium (VR, AR, etc.) and the operational context within the construction lifecycle (onsite tools, offsite monitoring and planning, simulation-based analysis, and workforce education). This dual classification is the first to systematically map immersive technology applications for occupational safety, specifically within horizontal transportation infrastructure. The findings of this review demonstrate the unique use cases of each immersive medium, revealing that VR is primarily used for controlled experimentation and full-immersion remote analysis, whereas AR and handheld devices are preferred for field-deployed applications. Despite these promising capabilities, widespread adoption remains limited by hardware constraints, challenging field conditions, and organizational resistance. This suggests that future work should focus on safety systems tested in real-world settings and rigorously evaluated by domain experts to enable their integration into standard workplace risk management practices.