WorldCuisines: Multilingual Visual Question Answering on Global Cuisines

WorldCuisines is a massive-scale benchmark for multilingual and multicultural visual question answering focused on global cuisines. The associated paper was accepted to NAACL 2025 and received the Best Theme Paper award. The dataset was last updated on November 14, 2025.

Use Cases

• Train visual question answering models based on images of global cuisines.
• Benchmark model performance on multilingual and multicultural visual understanding tasks.
• Research cultural and linguistic diversity in AI systems based on the dataset's theme.

Strengths

• Described as a 'massive-scale' benchmark, suggesting a large volume of data.
• Received the Best Theme Paper award at NAACL 2025, indicating academic recognition.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and dataset size are unknown, which may limit suitability assessment.

Provenance

Source

worldcuisines

Freshness

Last updated 2025-11-14 06:31:14

Geography

Global