Browse State-of-the-Art › Key Information Extraction
Key Information Extraction
40 papers with code · 6 benchmarks · 12 datasets archive 2025-07-28
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.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
6 leaderboard tables shown for this task, 6 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): CORD (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| CORD (9 rows) | RORE (GeoLayoutLM) | Modeling Layout Reading Order as Ordering Relations for... | code | — | Compare |
| SROIE (5 rows) | LayoutLMv2LARGE (Excluding OCR mismatch) | LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document... | code | — | Compare |
| Kleister NDA (3 rows) | LayoutLMv2LARGE | LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document... | code | — | Compare |
| EPHOIE (1 row) | LayoutLMv3 | LayoutLMv3: Pre-training for Document AI with Unified Text and... | code | — | Compare |
| ETD500 (1 row) | CRF-visual | Automatic Metadata Extraction Incorporating Visual Features from... | code | — | Compare |
| SIMARA (1 row) | DAN | SIMARA: a database for key-value information extraction from full pages | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
12 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 74 · with a code link: 40 · where Syntology ran a sample: 9 (7 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (9 of 74 tagged: 7 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 74 of 74, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
31 Dec 2019 19 repositories listed Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)In this paper, we propose the LayoutLM to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding…
-
29 Dec 2020 9 repositories listedPre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born…
-
28 Feb 2022 5 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)LiLT can be pre-trained on the structured documents of a single language and then directly fine-tuned on other languages with the corresponding off-the-shelf monolingual/multilingual pre-trained textual models.
-
18 Apr 2022 4 repositories listedIn this paper, we propose LayoutLMv3 to pre-train multimodal Transformers for Document AI with unified text and image masking.
-
27 May 2024 2 repositories listedIn the domain of Document AI, parsing semi-structured image form is a crucial Key Information Extraction (KIE) task.
-
17 Oct 2023 2 repositories listedHowever, BIO-tagging scheme relies on the correct order of model inputs, which is not guaranteed in real-world NER on scanned VrDs where text are recognized and arranged by OCR systems.
-
12 Oct 2022 2 repositories listed Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 1 pointer-only (licence)Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding.
-
10 Aug 2021 2 repositories listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 13 harvested samples)On the other hand, this paper tackles the problem by going back to the basic: effective combination of text and layout.
-
1 Jul 2021 2 repositories listedOur experiments show that CRF with visual features outperformed both a heuristic and a CRF model with only text-based features.
-
26 Mar 2021 2 repositories listedIn order to roundly evaluate our proposed method as well as boost the future research, we release a new dataset named WildReceipt, which is collected and annotated tailored for the evaluation of key information…
-
16 Apr 2020 2 repositories listed Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 1 pointer-only (licence)Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently.
-
8 Jul 2025 1 repository listedThis technical report introduces PaddleOCR 3.
-
26 Jun 2025 1 repository listedDocument understanding and analysis have received a lot of attention due to their widespread application.
-
22 Feb 2025 1 repository listedIn this paper, we introduce OmniParser V2, a universal model that unifies VsTP typical tasks, including text spotting, key information extraction, table recognition, and layout analysis, into a unified framework.
-
2 Oct 2024 1 repository listedKey information extraction (KIE) from visually rich documents (VRD) has been a challenging task in document intelligence because of not only the complicated and diverse layouts of VRD that make the model hard to…
-
29 Sep 2024 1 repository listedHowever, we argue that this formulation does not adequately convey the complete reading order information in the layout, which may potentially lead to performance decline in downstream VrD tasks.
-
11 Sep 2024 1 repository listedThis paper presents a novel approach to information extraction (IE) from visually rich documents (VRD) by employing a directed weighted graph representation to capture relationships among various VRD components.
-
2 Jul 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)However, existing methods that integrate spatial layouts with text have limitations, such as producing overly long text sequences or failing to fully leverage the autoregressive traits of LLMs.
-
1 May 2024 1 repository listedIn recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains.
-
28 Mar 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)Recently, visually-situated text parsing (VsTP) has experienced notable advancements, driven by the increasing demand for automated document understanding and the emergence of Generative Large Language Models (LLMs)…
-
7 Mar 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks.
-
2 Feb 2024 1 repository listedNamed Entity Recognition (NER) is a key information extraction task with a long-standing tradition.
-
7 Jan 2024 1 repository listedHowever, simply concatenating SER and RE serially can lead to severe error propagation, and it fails to handle cases like multi-line entities in real scenarios.
-
5 Jan 2024 1 repository listedThis paper introduces a novel system for information extraction from visually rich documents (VRD) using a weighted graph representation.
-
1 Jan 2024 1 repository listedRecently visually-situated text parsing (VsTP) has experienced notable advancements driven by the increasing demand for automated document understanding and the emergence of Generative Large Language Models (LLMs)…
-
25 Oct 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)We assess the model's performance across a range of OCR tasks, including scene text recognition, handwritten text recognition, handwritten mathematical expression recognition, table structure recognition, and…
-
24 Oct 2023 1 repository listedKey information extraction (KIE) from scanned documents has gained increasing attention because of its applications in various domains.
-
18 Sep 2023 1 repository listedIn this paper, we present AMuRD, a novel multilingual human-annotated dataset specifically designed for information extraction from receipts.
-
13 May 2023 1 repository listedIn this paper, we conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks including Text Recognition, Scene Text-Centric Visual Question Answering…
-
28 Apr 2023 1 repository listedAdvances in the Visually-rich Document Understanding (VrDU) field and particularly the Key-Information Extraction (KIE) task are marked with the emergence of efficient Transformer-based approaches such as the LayoutLM…
-
21 Apr 2023 1 repository listed
-
4 Apr 2023 1 repository listed
-
11 Feb 2023 1 repository listed
-
9 Nov 2022 1 repository listed
-
11 Oct 2022 1 repository listed
-
23 Aug 2022 1 repository listed
-
14 Aug 2021 1 repository listed
-
9 Jun 2021 1 repository listed
-
18 Mar 2021 1 repository listed
-
19 Feb 2020 1 repository listed
-
Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models27 Apr 2025 0 repositories listed
-
Emergency Communication: OTFS-Based Semantic Transmission with Diffusion Noise Suppression10 Apr 2025 0 repositories listed
-
KIEval: Evaluation Metric for Document Key Information Extraction7 Mar 2025 0 repositories listed
-
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy3 Dec 2024 0 repositories listed
-
"What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs20 Oct 2024 0 repositories listed
-
See then Tell: Enhancing Key Information Extraction with Vision Grounding29 Sep 2024 0 repositories listed
-
ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents23 Sep 2024 0 repositories listed
-
Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review23 Jul 2024 0 repositories listed
-
Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use30 May 2024 0 repositories listed
-
16 Apr 2024 0 repositories listed
-
RealKIE: Five Novel Datasets for Enterprise Key Information Extraction29 Mar 2024 0 repositories listed
-
Construction of a Syntactic Analysis Map for Yi Shui School through Text Mining and Natural Language Processing Research16 Feb 2024 0 repositories listed
-
15 Feb 2024 0 repositories listed
-
UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents17 Jan 2024 0 repositories listed
-
DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency9 Nov 2023 0 repositories listed
-
VKIE: The Application of Key Information Extraction on Video Text18 Oct 2023 0 repositories listed
-
PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction5 Oct 2023 0 repositories listed
-
Data Efficient Training of a U-Net Based Architecture for Structured Documents Localization2 Oct 2023 0 repositories listed
-
PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts20 Jul 2023 0 repositories listed
-
End-to-End Document Classification and Key Information Extraction using Assignment Optimization1 Jun 2023 0 repositories listed
-
30 May 2023 0 repositories listed
-
23 May 2023 0 repositories listed
-
26 Apr 2023 0 repositories listed
-
Information Extraction from Documents: Question Answering vs Token Classification in real-world setups21 Apr 2023 0 repositories listed
-
13 Apr 2023 0 repositories listed
-
NCU1415 at ROCLING 2022 Shared Task: A light-weight transformer-based approach for Biomedical Name Entity Recognition1 Nov 2022 0 repositories listed
-
Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections7 Oct 2022 0 repositories listed
-
RDU: A Region-based Approach to Form-style Document Understanding14 Jun 2022 0 repositories listed
-
Relational Representation Learning in Visually-Rich Documents5 May 2022 0 repositories listed
-
5 Jan 2022 0 repositories listed
-
19 Oct 2021 0 repositories listed
-
One-shot Key Information Extraction from Document with Deep Partial Graph Matching26 Sep 2021 0 repositories listed
-
ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents25 May 2021 0 repositories listed
-
12 May 2021 0 repositories listed
Syntology lines on 9 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections