Datasets › MaRVL

MaRVL (Multicultural Reasoning over Vision and Language)

Introduced by Fangyu Liu et al. in Visually Grounded Reasoning across Languages and Cultures28 Sep 2021 archive 2025-07-28

Multicultural Reasoning over Vision and Language (MaRVL) is a dataset based on an ImageNet-style hierarchy representative of many languages and cultures (Indonesian, Mandarin Chinese, Swahili, Tamil, and Turkish). The selection of both concepts and images is entirely driven by native speakers. Afterwards, we elicit statements from native speakers about pairs of images. The task consists in discriminating whether each grounded statement is true or false.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Zero-Shot Cross-Lingual Transfer MaRVL xUNITER Accuracy (%) 56.1 Visually Grounded Reasoning across Languages and Cultures e-bug/volta +2 2 Compare

Papers archive 2025-07-28

1 shown of 1 paper with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 29. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Visually Grounded Reasoning across Languages and Cultures 3 2 28 Sep 2021 ran 0 of 4 samples (4 unverified)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY 4.0 license

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • MaRVL

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections