jonathan-roberts1/GPT4GEO

Accompanying repo for NeurIPSW'23: GPT4GEO: How a Language Model Sees the World's Geography

32
/ 100
Emerging

This project explores how a large language model like GPT-4 understands geography without internet access. It takes natural language questions about places, distances, routes, and demographics, and outputs structured information such as coordinates, travel plans, or population figures. Geographers, urban planners, logistics managers, and travel professionals can use this to understand a model's inherent geographic knowledge.

No commits in the last 6 months.

Use this if you are interested in the baseline geographic knowledge and reasoning capabilities of large language models for tasks like route planning, demographic queries, or mapping.

Not ideal if you require real-time, up-to-the-minute geographical data or need to incorporate external, live data sources for your analysis.

geographical-analysis route-planning demographic-research logistics-modeling travel-itinerary
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

27

Forks

2

Language

License

MIT

Last pushed

May 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/jonathan-roberts1/GPT4GEO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.