Natural Language Inference on TabFact (test)
77.1AccuracyGPT-4+OCR
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4+OCRModel Size=~1T, Modality=Text, Evaluation Setting=Zero-Shot (ZS)2023.12 | 77.1 | |
| UReaderModel Size=~7B, Modality=Text+Vision, Evaluation Setting=SDDS2023.12 | 67.6 | |
| DocLLM-7BModel Size=7B, Modality=Text+Layout, Evaluation Setting=SDDS2023.12 | 66.4 | |
| mPLUG-DocOwlModel Size=~7B, Modality=Text+Vision, Evaluation Setting=SDDS2023.12 | 60.2 | |
| DocLLM-1BModel Size=1B, Modality=Text+Layout, Evaluation Setting=SDDS2023.12 | 58 | |
| Llama2+OCRModel Size=7B, Modality=Text, Evaluation Setting=Zero-Shot (ZS)2023.12 | 48.2 |