# PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval

**Authors:** He Zhu, Wenjia Zhang, Nuoxian Huang, Boyang Li, Luyao Niu, Zipei Fan, Tianle Lun, Yicheng Tao, Junyou Su, Zhaoya Gong, Chenyu Fang, Xing Liu  
**arXiv:** [2402.19273](https://arxiv.org/abs/2402.19273)  
**Date:** 2024-02-29  
**Summary page:** https://www.summarizepaper.com/en/paper/2402.19273v1/

## Key points

- PlanGPT is a specialized Large Language Model designed for urban planners
- Developed in collaboration with esteemed institutions like the Chinese Academy of Urban Planning
- Features a customized local database retrieval framework for quick and accurate access to relevant information
- Undergoes domain-specific fine-tuning to provide tailored responses for urban planning tasks
- Boasts advanced tooling capabilities to enhance performance
- Empirical tests demonstrate consistent delivery of superior quality responses

## Summary

PlanGPT is a groundbreaking specialized Large Language Model designed to address the unique challenges faced by urban planners. It was developed through collaborative efforts with esteemed institutions like the Chinese Academy of Urban Planning to bridge the gap and enhance the efficiency of urban professionals. One of its key features is a customized local database retrieval framework that allows for quick and accurate access to pertinent information specific to urban planning. Additionally, PlanGPT undergoes domain-specific fine-tuning of base models to provide tailored responses that meet high standards in urban and spatial planning. Moreover, it boasts advanced tooling capabilities that further enhance its performance. Empirical tests have shown that PlanGPT consistently delivers superior quality responses, showcasing its ability to generate precise and relevant content for urban planning tasks.