Applications of large language models and generative AI in transportation: A systematic review and bibliometric analysis

• This study provides the first systematic and bibliometric review of LLM and GenAI applications in transportation. • A total of 65 studies (2023–2024) were examined and classified into themes of traffic management, autonomous driving, and safety. • Findings show LLMs’ transformative potential in traffic prediction, crash analysis, and risk perception using multimodal data. • Key challenges include high computational needs, limited data, scalability issues, and cybersecurity risks in transport. • Future research will focus on lightweight architectures, better multimodal integration, and privacy in smart mobility. The integration of Large Language Models (LLMs) and Generative AI (GenAI) in transportation has gained significant attention, particularly in applications related to traffic safety, intelligent transportation systems, and autonomous driving. This paper provides a bibliometric analysis and systematic review of the current literature on LLM-based applications in transportation, analyzing 65 relevant studies published between 2023 and 2024 from Scopus and Web of Science. The review categorizes existing applications into three primary thematic areas: Traffic (28 studies), Autonomous Driving (23), and Safety (15). The findings highlight the transformative role of LLMs in traffic prediction, crash analysis, and risk perception, demonstrating their ability to process large-scale, multimodal datasets with improved efficiency and adaptability. Additionally, this study explores challenges such as computational demands, data limitations, model scalability, and cybersecurity concerns, providing insights into emerging solutions for real-time traffic management, accident prevention, and human-AI interaction in autonomous systems. The review concludes by identifying key research gaps and future directions, emphasizing the need for lightweight AI models, enhanced multimodal integration, and privacy-preserving frameworks to advance LLM applications in smart and sustainable transportation systems.