Document Information Extraction on VRDU Registration Form Single
93.97Micro-F1LMDXPaLM 2-S
Evaluation Results
| Method | Links | |
|---|---|---|
| LMDXPaLM 2-S|D| (Training Data Size)=100, Modality=T+L, Localized?=true2023.09 | 93.97 | |
| LMDXPaLM 2-S|D| (Training Data Size)=200, Modality=T+L, Localized?=true2023.09 | 93.97 | |
| LMDXPaLM 2-S|D| (Training Data Size)=50, Modality=T+L, Localized?=true2023.09 | 93.06 | |
| FormNet|D| (Training Data Size)=200, Modality=T+L, Localized?=true2023.09 | 92.12 | |
| LayoutLMv2|D| (Training Data Size)=200, Modality=T+L+I, Localized?=true2023.09 | 91.41 | |
| FormNet|D| (Training Data Size)=100, Modality=T+L, Localized?=true2023.09 | 90.91 | |
| LayoutLMv3|D| (Training Data Size)=200, Modality=T+L+I, Localized?=true2023.09 | 90.89 | |
| LMDXPaLM 2-S|D| (Training Data Size)=10, Modality=T+L, Localized?=true2023.09 | 90.88 | |
| LayoutLM|D| (Training Data Size)=200, Modality=T+L+I, Localized?=true2023.09 | 90.47 | |
| LayoutLMv2|D| (Training Data Size)=100, Modality=T+L+I, Localized?=true2023.09 | 90.45 | |
| FormNet|D| (Training Data Size)=50, Modality=T+L, Localized?=true2023.09 | 89.38 | |
| LayoutLMv3|D| (Training Data Size)=100, Modality=T+L+I, Localized?=true2023.09 | 89.23 | |
| LayoutLM|D| (Training Data Size)=100, Modality=T+L+I, Localized?=true2023.09 | 88.7 | |
| LayoutLMv2|D| (Training Data Size)=50, Modality=T+L+I, Localized?=true2023.09 | 88.68 | |
| LayoutLMv3|D| (Training Data Size)=50, Modality=T+L+I, Localized?=true2023.09 | 87.24 | |
| LayoutLM|D| (Training Data Size)=50, Modality=T+L+I, Localized?=true2023.09 | 86.21 | |
| LayoutLMv2|D| (Training Data Size)=10, Modality=T+L+I, Localized?=true2023.09 | 80.05 | |
| LMDXGemini Pro|D| (Training Data Size)=0, Modality=T+L, Localized?=true2023.09 | 76.78 | |
| FormNet|D| (Training Data Size)=10, Modality=T+L, Localized?=true2023.09 | 74.22 | |
| LMDXPaLM 2-S|D| (Training Data Size)=0, Modality=T+L, Localized?=true2023.09 | 73.81 | |
| Gemini Pro+OCR|D| (Training Data Size)=0, Modality=T, Localized?=false2023.09 | 73.62 | |
| LayoutLMv3|D| (Training Data Size)=10, Modality=T+L+I, Localized?=true2023.09 | 72.51 | |
| GPT-4V+Image|D| (Training Data Size)=0, Modality=I, Localized?=false2023.09 | 68.97 | |
| GPT-3.5+OCR|D| (Training Data Size)=0, Modality=T, Localized?=false2023.09 | 67.23 | |
| LayoutLM|D| (Training Data Size)=10, Modality=T+L+I, Localized?=true2023.09 | 65.91 | |
| PaLM 2-S+OCR|D| (Training Data Size)=0, Modality=T, Localized?=false2023.09 | 62.8 | |
| Gemini Pro+Image|D| (Training Data Size)=0, Modality=I, Localized?=false2023.09 | 53.9 | |
| LLaVA-v1.5-13B+Image|D| (Training Data Size)=0, Modality=I, Localized?=false2023.09 | 5.29 |