Large Language Models for Mobility Analysis in Transportation Systems: A Survey on Forecasting Tasks

TL;DR

This survey addresses how Large Language Models can contribute to forecasting mobility in transportation systems by organizing data processing and model framework approaches for time-series tasks. It categorizes applications into traffic forecasting, human mobility, demand forecasting, and missing-data imputation, and reviews methods such as tokenization, prompting, embeddings, fine-tuning, zero-shot/few-shot, and integration with downstream models. It highlights representative systems and architectures like AuxMobLCast, TrafficGPT, ST-LLM, STG-LLM, GT-TDI, and TPLLM, and discusses interpretability, privacy, data availability, and open data needs. The work advocates integrating transportation-domain knowledge with LLMs to enable scalable, privacy-preserving, and interoperable LLM-based mobility forecasting and outlines directions for future research and standardized datasets.

Abstract

Mobility analysis is a crucial element in the research area of transportation systems. Forecasting traffic information offers a viable solution to address the conflict between increasing transportation demands and the limitations of transportation infrastructure. Predicting human travel is significant in aiding various transportation and urban management tasks, such as taxi dispatch and urban planning. Machine learning and deep learning methods are favored for their flexibility and accuracy. Nowadays, with the advent of large language models (LLMs), many researchers have combined these models with previous techniques or applied LLMs to directly predict future traffic information and human travel behaviors. However, there is a lack of comprehensive studies on how LLMs can contribute to this field. This survey explores existing approaches using LLMs for time series forecasting problems for mobility in transportation systems. We provide a literature review concerning the forecasting applications within transportation systems, elucidating how researchers utilize LLMs, showcasing recent state-of-the-art advancements, and identifying the challenges that must be overcome to fully leverage LLMs in this domain.

Figures (2)

• Figure 1: Traffic Forcasting Technology Development ahmed1979analysisazari2019cellularwang2014newsun2002shortzhang2009traffictang2019trafficalajali2018intersectionxia2017trafficdalgkitsis2018trafficli2017diffusionyu2016datajiang2023graphchen2003traffichaydari2024mobilitygptzhang2023spatioliu2024spatialguo2024explainablezhang2024semanticyu1993trafficlv2014trafficxue2022leveraging
• Figure 2: Overview of methodologies in LLM pipeline for time series forecasting in Transportation Systems