ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing

2026-06-13

AI Summary

This study addresses the challenge that existing public transit routing methods struggle to effectively model diverse user preferences. To bridge this gap, we propose the first personalized route planning framework that integrates natural language understanding with transportation optimization. Our approach leverages a fine-tuned large language model (LLM) enhanced with retrieval-augmented generation (RAG) to accurately extract user preferences from ambiguous or conversational queries and map them into structured routing parameters, which are then incorporated into a multi-objective optimization function. To support this work, we introduce the first preference-aware dataset encompassing multiple user roles and real-world scenarios. Experimental results demonstrate that our system significantly outperforms existing methods in both preference interpretation accuracy and generation of feasible routes, while also uncovering higher-value alternative paths across additional dimensions of user preference.

Abstract

Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into routing algorithms. This paper presents ChatPlanner, a novel framework that leverages Large Language Models (LLMs) to enable preference aware public transit routing. Our approach employs fine-tuned LLMs with Retrieval-Augmented Generation (RAG) to extract routing parameters and interpret nuanced user preferences from natural language queries, subsequently integrating these preferences into the objective function of a public transit routing algorithm. This study designs preference aware datasets incorporating eight personas and five contexts to establish scoring standards for both fine-tuning and RAG. This work conducted three experiments to validate the solutions' feasibility, extraction of routing information and preferences, and solution set quality and completeness. Results demonstrate that ChatPlanner generates feasible solutions reliably. Fine-tuning enforces the required output structure and learns general preference patterns, while RAG provides query-specific context to resolve imprecise or conversational expressions and calibrate continuous scores. The combination of both achieves the highest accuracy in routing information extraction and user preference interpretation. Results based on selected case studies show that by capturing user preferences, ChatPlanner identifies valuable solutions across different dimensions that existing route planners overlook, generating more valuable route alternatives. This research establishes a new paradigm for integrating natural language understanding into transportation optimization.

Problem

• personalized public transit routing
• user preferences
• Large Language Models
• natural language queries
• transportation optimization

Innovation

• Large Language Models
• Retrieval-Augmented Generation
• Personalized Transit Routing
• Preference-aware Optimization
• Natural Language Understanding