用大模型让普通人能自然语言查询公交数据
TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models
- 用提示词引导大模型生成代码，自动处理公交数据
- 100项任务测试中，GPT-4o和Claude-3.5准确率超90%
- 适合交通研究者、城市规划者快速分析公交信息
本文提出一个基于大语言模型（LLM）的框架，通过聊天机器人TransitGPT实现对通用公交数据规范（GTFS）的自然语言查询。该框架在服务器上执行由大模型生成的Python代码，完成数据提取、计算与交互式可视化，无需用户具备编程或GTFS知识。所有代码生成均依赖提示词，未进行微调也无访问实际数据源。在包含100个任务的基准测试中，使用GPT-4o和Claude-3.5-Sonnet评估，结果显示TransitGPT显著提升了公共交通数据的可访问性与可用性。
原文摘要 · Abstract (English)
This paper introduces a framework that leverages Large Language Models (LLMs) to answer natural language queries about General Transit Feed Specification (GTFS) data. The framework is implemented in a chatbot called TransitGPT with open-source code. TransitGPT works by guiding LLMs to generate Python code that extracts and manipulates GTFS data relevant to a query, which is then executed on a server where the GTFS feed is stored. It can accomplish a wide range of tasks, including data retrieval, calculations, and interactive visualizations, without requiring users to have extensive knowledge of GTFS or programming. The LLMs that produce the code are guided entirely by prompts, without fine-tuning or access to the actual GTFS feeds. We evaluate TransitGPT using GPT-4o and Claude-3.5-Sonnet LLMs on a benchmark dataset of 100 tasks, to demonstrate its effectiveness and versatility. The results show that TransitGPT can significantly enhance the accessibility and usability of transit data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。