Exploring the Potential of Large Language Models in Public Transportation: San Antonio Case Study

TL;DR

This study investigates the potential of large language models to augment public transportation in San Antonio by leveraging GTFS data for understanding and information retrieval tasks. Using OpenAI's ChatGPT variants (GPT-3.5-turbo and GPT-4o), the authors conduct five experiments on 3275 MCQs and 80 short-answer questions, comparing pre-trained versus augmented data and evaluating retrieval across multi-file GTFS queries. Results show GPT-4o generally outperforms GPT-3.5-turbo on larger datasets, while augmentation with 'none of these' reduces accuracy, and simple retrieval tasks are relatively robust but complex data integration remains challenging. The findings underscore substantial promise for LLM-assisted transit services, while highlighting critical needs in prompt engineering, data handling, and ethics before real-world deployment in public transportation. The San Antonio case study provides actionable insights for applying LLM-powered transit solutions in other growing urban environments.

Abstract

The integration of large language models (LLMs) into public transit systems presents a transformative opportunity to enhance urban mobility. This study explores the potential of LLMs to revolutionize public transportation management within the context of San Antonio's transit system. Leveraging the capabilities of LLMs in natural language processing and data analysis, we investigate their capabilities to optimize route planning, reduce wait times, and provide personalized travel assistance. By utilizing the General Transit Feed Specification (GTFS) and other relevant data, this research aims to demonstrate how LLMs can potentially improve resource allocation, elevate passenger satisfaction, and inform data-driven decision-making in transit operations. A comparative analysis of different ChatGPT models was conducted to assess their ability to understand transportation information, retrieve relevant data, and provide comprehensive responses. Findings from this study suggest that while LLMs hold immense promise for public transit, careful engineering and fine-tuning are essential to realizing their full potential. San Antonio serves as a case study to inform the development of LLM-powered transit systems in other urban environments.

Figures (1)

• Figure 1: Summary of performance by question type for GPT 3.5-turbo and GPT-4o on GTFS Retrieval Benchmark.