List your company
ResearchFormerly WizWand

Information Extraction on FUNSD (test)

92.08F1 ScoreLayoutLMv3large
-1.904822.495146.89571.2949Dec 5, 2022Apr 27, 2023Sep 18, 2023Feb 8, 2024Jul 1, 2024Nov 21, 2024Apr 14, 2025
Updated 8mo ago

Evaluation results

MethodLinks
LayoutLMv3largeModality=Vision+Text+Layout2022.1292.08
LayoutLMv3Model Category=Fine-tuned PTM, Evaluation Protocol=Fine-tuned2024.0492.08
UDOPModality=Vision+Text+Layout2022.1291.62
LayoutLMv3 BaseModality=Vision + Text + Layout, Pretrain Data=11M2023.0990.29
LILTModality=Text+Layout2022.1288.41
LiLT BaseModality=Text + Layout, Pretrain Data=11M2023.0988.41
GraphDocResnetModality=Vision + Text + Layout, Pretrain Data=320k2023.0987.95
UniDocModality=Vision+Text+Layout2022.1287.93
UDocModality=Vision + Text + Layout, Pretrain Data=11M2023.0987.93
GraphDocModality=Vision + Text + Layout, Pretrain Data=320k2023.0987.77
StructuralLMlargeModality=Text+Layout2022.1285.14
FormNetModality=Text+Layout2022.1284.69
FormNetModality=Text + Layout, Pretrain Data=700k2023.0984.69
DocFormerlargeModality=Vision+Text+Layout2022.1284.55
BROSlargeModality=Text+Layout2022.1284.52
LayoutLMv2largeModality=Vision+Text+Layout2022.1284.2
SelfDocModality=Vision+Text+Layout2022.1283.36
SelfDocModality=Vision + Text + Layout, Pretrain Data=320k2023.0983.36
DocFormer BaseModality=Vision + Text + Layout, Pretrain Data=5M2023.0983.34
LayoutLMv2 BaseModality=Vision + Text + Layout, Pretrain Data=11M2023.0982.76
BROSModality=Text + Layout, Pretrain Data=11M2023.0981.21
DocFormer BaseModality=Text + Layout, Pretrain Data=5M2023.0980.54
LayoutLLM-7BModel Category=Ours, Evaluation Protocol=Zero-shot, Backbone Initialization=Vicuna-1.5-7B2024.0479.98
GlobalDoc (V+T)Modality=Vision + Text, Pretrain Data=1.4M2023.0979.4
LayoutLMv1 BaseModality=Vision + Text + Layout, Pretrain Data=11M2023.0979.27
LayoutLMv1 BaseModality=Text + Layout, Pretrain Data=11M2023.0978.66
LayoutLLM-7BModel Category=Ours, Evaluation Protocol=Zero-shot, Backbone Initialization=Llama2-7B-chat2024.0478.65
LayoutLMlargeModality=Text+Layout2022.1277.89
GlobalDoc (V+T)Modality=Vision + Text, Pretrain Data=320k2023.0977.84
BERTlargeModality=Text2022.1266.63
ROBERTabaseModality=Text2023.0966.48
Qwen2-VL-7B+zero-shot=true, RIDGE fine-tuned=true2025.0466.48
GlobalDoc (T)Modality=Text, Pretrain Data=1.4M2023.0965.52
GlobalDoc (T)Modality=Text, Pretrain Data=320k2023.0962.27
BERT BaseModality=Text2023.0960.26
Qwen2-VL-7Bzero-shot=true, RIDGE fine-tuned=false2025.0459.89
Vicuna-1.5-7BModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.0459.63
Llama2-7B-chatModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.0458.34
DocLLM-7BModel Size=7B, Modality=Text+Layout, Evaluation Setting=SDDS2023.1251.8
Llama2-7BModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.0451.4
DocOwl-1.5-Chatzero-shot=true, RIDGE fine-tuned=false2025.0450.88
Vicuna-7BModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.0449.79
DocLLM-1BModel Size=1B, Modality=Text+Layout, Evaluation Setting=SDDS2023.1248.2
Llama2-7B-chatModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.0448.2
Vicuna-1.5-7BModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.0448.06
Qwen-VL-7BModel Category=MLLM, Evaluation Protocol=Fine-tuned, Implementation=Original Paper2024.0447.09
Vicuna-7BModel Category=LLM, Input Representation=Layout Text (Text + Box), Evaluation Protocol=Zero-shot2024.0442.73
Llama2-7BModel Category=LLM, Input Representation=Plain Text, Evaluation Protocol=Zero-shot2024.0440.78
GPT-4+OCRModel Size=~1T, Modality=Text, Evaluation Setting=Zero-Shot (ZS)2023.1237
Monkeyzero-shot=true, RIDGE fine-tuned=false2025.0434.27
LLaVA-NeXT-Mistral-7B+zero-shot=true, RIDGE fine-tuned=true2025.0433.41
LLaVA-NeXT-Mistral-7Bzero-shot=true, RIDGE fine-tuned=false2025.0431.18
Llama2+OCRModel Size=7B, Modality=Text, Evaluation Setting=Zero-Shot (ZS)2023.1217.8
LLaVA-1.5-7BModel Category=MLLM, Evaluation Protocol=Zero-shot2024.041.93
LLaVAR-7BModel Category=MLLM, Evaluation Protocol=Zero-shot, Implementation=Original Paper2024.041.71