DocVQA consists of 50,000 questions defined on 12,000+ document images.
Variants: DocVQA val, DocVQA test, DocVQA
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Visual Question Answering (VQA) | ChatGPT 3.5 with LAPDoc Prompt (SpatialFormat) | LAPDoc: Layout-Aware Prompting for Documents | 2024-02-15 |
Recent papers with results on this dataset: