Large Language Models for Traffic and Transportation Research: Methodologies, State of the Art, and Future Opportunities

2025-03-27

AI Summary

To address the absence of systematic surveys on large language models (LLMs) in transportation and traffic engineering, this paper presents the first comprehensive literature review covering LLM applications in this domain from 2023 to 2025. Methodologically, we propose a dual-dimensional “method–application” taxonomy that integrates zero-shot/few-shot learning, prompt engineering, and supervised fine-tuning, while coupling LLMs with traffic simulation tools and multimodal textual data (e.g., incident reports, operational logs, social media). Key contributions include: (1) synthesizing 12 representative application scenarios and 7 critical technical challenges; (2) identifying two pivotal research directions—hybrid integration of LLMs with classical traffic models and task-specific architectural customization for transportation; and (3) proposing an actionable, implementation-oriented research roadmap toward intelligent and sustainable transportation systems, explicitly delineating current technological boundaries and fundamental knowledge gaps.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The rapid rise of Large Language Models (LLMs) is transforming traffic and transportation research, with significant advancements emerging between the years 2023 and 2025 -- a period marked by the inception and swift growth of adopting and adapting LLMs for various traffic and transportation applications. However, despite these significant advancements, a systematic review and synthesis of the existing studies remain lacking. To address this gap, this paper provides a comprehensive review of the methodologies and applications of LLMs in traffic and transportation, highlighting their ability to process unstructured textual data to advance transportation research. We explore key applications, including autonomous driving, travel behavior prediction, and general transportation-related queries, alongside methodologies such as zero- or few-shot learning, prompt engineering, and fine-tuning. Our analysis identifies critical research gaps. From the methodological perspective, many research gaps can be addressed by integrating LLMs with existing tools and refining LLM architectures. From the application perspective, we identify numerous opportunities for LLMs to tackle a variety of traffic and transportation challenges, building upon existing research. By synthesizing these findings, this review not only clarifies the current state of LLM adoption and adaptation in traffic and transportation but also proposes future research directions, paving the way for smarter and more sustainable transportation systems.

Problem

• Reviewing LLM methodologies in traffic and transportation research
• Exploring LLM applications like autonomous driving and travel prediction
• Identifying research gaps and future directions for LLMs in transportation

Innovation

• LLMs process unstructured textual transportation data
• Zero-shot and few-shot learning for traffic applications
• Integrate LLMs with existing transportation tools