nvBench-Rob

The nvBench-Rob dataset is a comprehensive robustness evaluation dataset for text-to-vis models, containing diverse lexical and phrasal variations based on the original text-to-vis benchmark nvBench.

Data and Resources

Cite this as

Jinwei Lu, Yuanfeng Song, Haodi Zhang, Chen Zhang, Raymond Chi-Wing Wong (2025). Dataset: nvBench-Rob. https://doi.org/10.57702/dpml7btp

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.2404.07135
Author Jinwei Lu
More Authors
Yuanfeng Song
Haodi Zhang
Chen Zhang
Raymond Chi-Wing Wong