Key-value Pair Extraction

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

9 shown of 9 papers with code (12 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
  29 Dec 2020 9 repositories listed
  Pre-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…
• LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
  18 Apr 2021 6 repositories listed
  In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding.
• LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
  28 Feb 2022 5 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  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.
• OCR-free Document Understanding Transformer
  30 Nov 2021 5 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
• LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
  18 Apr 2022 4 repositories listed
  In this paper, we propose \textbf{LayoutLMv3} to pre-train multimodal Transformers for Document AI with unified text and image masking.
• Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
  17 Oct 2023 2 repositories listed
  However, 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.
• KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents
  1 May 2024 1 repository listed
  In recent years, the challenge of extracting information from business documents has emerged as a critical task, finding applications across numerous domains.
• PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
  7 Jan 2024 1 repository listed
  However, 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.
• GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
  21 Apr 2023 1 repository listed
  Additionally, novel relation heads, which are pre-trained by the geometric pre-training tasks and fine-tuned for RE, are elaborately designed to enrich and enhance the feature representation.

Syntology lines on 2 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. Read from the graph 2026-09-24.