SOTAVerified

Key Information Extraction

Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 74 papers

TitleStatusHype
PaddleOCR 3.0 Technical ReportCode0
Class-Agnostic Region-of-Interest Matching in Document ImagesCode0
Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models—0
Emergency Communication: OTFS-Based Semantic Transmission with Diffusion Noise Suppression—0
KIEval: Evaluation Metric for Document Key Information Extraction—0
OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language ModelsCode0
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy—0
"What is the value of templates?" Rethinking Document Information Extraction Datasets for LLMs—0
GraphRevisedIE: Multimodal Information Extraction with Graph-Revised NetworkCode0
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document UnderstandingCode1
Show:102550
← PrevPage 1 of 8Next →
All datasetsCORDSROIEKleister NDASIMARA

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LayoutLMv2LARGE (Excluding OCR mismatch)F197.81—Unverified
2RORE (GeoLayoutLM)F196.97—Unverified
3LayoutLMv2LARGEF196.61—Unverified
4LayoutLMv2BASEF196.25—Unverified
5ChatGPT 3.5 SpatialFormatAccuracy77—Unverified