← all datasets

e-SNLI-VE

Emerging
4papers using it
15HF downloads
1HF likes
2022first seen

The 'e-SNLI-VE' dataset is a benchmark that contains pairs of natural language explanations and visual inputs, used to evaluate the faithfulness of natural language explanations in vision-language tasks.

Papers using e-SNLI-VE (4)

e-SNLI-VE β€” datasets β€” multimodal