neulab/CulturalGround

This repository provides the official resources for EMNLP 2025 Paper Grounding Multilingual Multimodal LLMs With Cultural Knowledge

33
/ 100
Emerging

This project helps researchers and developers improve how large language models understand global cultures. It provides a dataset of 30 million visual question-answering pairs across 42 countries and 39 languages, and a fine-tuned model called CulturalPangea. Users can input images and questions about cultural entities to get more accurate, culturally-aware answers from the model.

No commits in the last 6 months.

Use this if you are building or evaluating multilingual, multimodal AI models and need them to accurately recognize and respond to culturally specific entities from diverse global backgrounds.

Not ideal if your primary focus is on general vision-language tasks without a specific emphasis on diverse cultural understanding.

cross-cultural communication global marketing AI model development multilingual AI cultural education
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Oct 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/neulab/CulturalGround"

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