ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing
Researchers have developed ChatPlanner, a new framework utilizing Large Language Models (LLMs) to create personalized public transit routing. This system employs fine-tuned LLMs with Retrieval-Augmented Generation (RAG) to interpret user preferences from natural language queries and integrate them into routing algorithms. Experiments show ChatPlanner reliably generates feasible solutions, with fine-tuning ensuring structural integrity and RAG providing query-specific context for improved accuracy in extracting routing information and user preferences. AI
IMPACT This framework could lead to more user-centric transportation planning tools by better integrating natural language understanding with optimization algorithms.