Visual Question Answering on DUDE (test)
0.546ANLSGPT-4+OCR
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4+OCRModel Size=~1T, Modality=Text, Evaluation Setting=Zero-Shot (ZS)2023.12 | 0.546 | |
| DocLLM-7BModel Size=7B, Modality=Text+Layout, Evaluation Setting=SDDS2023.12 | 0.472 | |
| DocLLM-1BModel Size=1B, Modality=Text+Layout, Evaluation Setting=SDDS2023.12 | 0.426 | |
| Llama2+OCRModel Size=7B, Modality=Text, Evaluation Setting=Zero-Shot (ZS)2023.12 | 0.381 |