Основные понятия
Urban planning tasks are enhanced through the specialized Large Language Model, PlanGPT, tailored for urban and spatial planning needs.
Аннотация
PlanGPT is a specialized Large Language Model designed for urban and spatial planning. It addresses challenges in urban planning texts by utilizing customized embedding models, vector database retrieval systems, and advanced tooling capabilities. The model aims to improve efficiency in tasks such as generating urban planning texts, retrieving information, and evaluating planning documents. PlanGPT has been developed through collaborative efforts with institutions like the Chinese Academy of Urban Planning. It leverages domain-specific fine-tuning of base models to deliver responses tailored to the intricacies of urban planning. The model has shown advanced performance in empirical tests, surpassing other state-of-the-art models.
Статистика
PlanGPT leverages a customized local database retrieval framework.
Empirical tests demonstrate that PlanGPT has achieved advanced performance.
PlanGPT features a customized embedding model for accurate information extraction.
The model employs instruction fine-tuning methods to activate interdisciplinary knowledge.
Experimental results have demonstrated that PlanGPT effectively addresses challenges in urban planning texts.
Цитаты
"Tasks like generating urban planning texts, retrieving related information, and evaluating planning documents pose unique challenges."
"We introduce PlanGPT, the first specialized Large Language Model tailored for urban and spatial planning."
"Empirical tests demonstrate that PlanGPT has achieved advanced performance."