ChatGPT, developed by OpenAI, is one of the milestone large language models (LLMs) with 6 billion parameters. ChatGPT has demonstrated the impressive language understanding capability of LLM, particularly in generating conversational response. As LLMs start to gain more attention in various research or engineering domains, it is time to envision how LLM may revolutionize the way we approach intelligent transportation systems. This paper explores the future applications of LLM in addressing key transportation problems. By leveraging LLM with cross-modal encoder, an intelligent system can also process traffic data from different modalities and execute transportation operations through an LLM. We present and validate these potential transportation applications equipped by LLM. To further demonstrate this potential, we also provide a concrete smartphone-based crash report auto-generation and analysis framework as a use case. Despite the potential benefits, challenges related to data privacy, data quality, and model bias must be considered. Overall, the use of LLM in intelligent transport systems holds promise for more efficient, intelligent, and sustainable transportation systems that further improve daily life around the world.

翻译：由OpenAI开发的ChatGPT是拥有60亿参数的里程碑式大型语言模型之一。ChatGPT展现了大型语言模型（LLM）令人印象深刻的语言理解能力，尤其是在生成对话式回复方面。随着LLM开始在各研究或工程领域获得更多关注，是时候展望LLM如何能彻底改变我们处理智能交通系统的方式。本文探讨了LLM在解决关键交通问题中的未来应用。通过将LLM与跨模态编码器相结合，智能系统也能处理来自不同模态的交通数据，并通过LLM执行交通操作。我们提出并验证了这些由LLM赋能的潜在交通应用。为进一步展示这一潜力，我们还提供了一个基于智能手机的具体事故报告自动生成与分析框架作为用例。尽管存在潜在优势，但数据隐私、数据质量和模型偏差等挑战必须加以考量。总体而言，在智能交通系统中应用LLM有望构建更高效、智能和可持续的交通系统，从而进一步改善全球日常生活。