Key Information Extraction on RFUND-EN

Metric: key-value pair F1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	key-value pair F1▼	Extra Data	Paper	Date↕	Code
1	PEneo (LayoutLMv3_base)	79.27	No	PEneo: Unifying Line Extraction, Line Grouping, ...	2024-01-07	Code
2	PEneo (LiLT[InfoXLM]_base)	74.29	No	PEneo: Unifying Line Extraction, Line Grouping, ...	2024-01-07	Code
3	PEneo (LayoutXLM_base)	74.25	No	PEneo: Unifying Line Extraction, Line Grouping, ...	2024-01-07	Code
4	PEneo (LiLT[EN-R]_base)	74.22	No	PEneo: Unifying Line Extraction, Line Grouping, ...	2024-01-07	Code
5	PEneo (LayoutLMv2_base)	71.97	No	PEneo: Unifying Line Extraction, Line Grouping, ...	2024-01-07	Code
6	GeoLayoutLM	69.03	No	GeoLayoutLM: Geometric Pre-training for Visual I...	2023-04-21	Code
7	LayoutLMv3	57.66	No	LayoutLMv3: Pre-training for Document AI with Un...	2022-04-18	Code
8	LiLT ([EN-R]_base)	54.33	No	LiLT: A Simple yet Effective Language-Independen...	2022-02-28	Code
9	LayoutXLM_base	53.98	No	LayoutXLM: Multimodal Pre-training for Multiling...	2021-04-18	Code
10	LiLT ([InfoXLM]_base)	52.18	No	LiLT: A Simple yet Effective Language-Independen...	2022-02-28	Code
11	TPP (LayoutLMv3_base)	50.27	No	Reading Order Matters: Information Extraction fr...	2023-10-17	Code
12	LayoutLMv2_base	49.06	No	LayoutLMv2: Multi-modal Pre-training for Visuall...	2020-12-29	Code
13	Donut	24.54	No	OCR-free Document Understanding Transformer	2021-11-30	Code

#1PEneo (LayoutLMv3_base)SOTA
79.27
key-value pair F1· 2024-01-07
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction Code
#2PEneo (LiLT[InfoXLM]_base)
74.29
key-value pair F1· 2024-01-07
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction Code
#3PEneo (LayoutXLM_base)
74.25
key-value pair F1· 2024-01-07
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction Code
#4PEneo (LiLT[EN-R]_base)
74.22
key-value pair F1· 2024-01-07
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction Code
#5PEneo (LayoutLMv2_base)
71.97
key-value pair F1· 2024-01-07
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction Code
#6GeoLayoutLMSOTA
69.03
key-value pair F1· 2023-04-21
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction Code
#7LayoutLMv3SOTA
57.66
key-value pair F1· 2022-04-18
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking Code
#8LiLT ([EN-R]_base)SOTA
54.33
key-value pair F1· 2022-02-28
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding Code
#9LayoutXLM_baseSOTA
53.98
key-value pair F1· 2021-04-18
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding Code
#10LiLT ([InfoXLM]_base)
52.18
key-value pair F1· 2022-02-28
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding Code
#11TPP (LayoutLMv3_base)
50.27
key-value pair F1· 2023-10-17
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction Code
#12LayoutLMv2_baseSOTA
49.06
key-value pair F1· 2020-12-29
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding Code
#13Donut
24.54
key-value pair F1· 2021-11-30
OCR-free Document Understanding Transformer Code