MultiModalQA

The 'MultiModalQA' dataset/benchmark contains multimodal data that is used to evaluate question answering tasks requiring reasoning across multiple modalities, such as text and visual information.

Papers using MultiModalQA (4)

VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering2025Multimodal Graph Transformer for Multimodal Question Answering2023 · 7 citesMoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model2023 · 4 citesMMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images2023 · 2 cites