Challenge: Existing models for structured information extraction are limited by narrow entity ontologies, simple queries, or homogeneous document types.
Approach: They propose a benchmark dataset for structured Information Extraction (IE) from document images . they analyze open and closed VLMs on this benchmark .
Outcome: The proposed model can perform fine-grained structured extraction across document types and schemas.

Similar Papers

Learning to Extract Structured Entities Using Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Language Models (LMs) play a pivotal role in extracting structured information from unstructured text.
Approach: They propose to reformulate the task to be entity-centric, enabling the use of diverse metrics that can provide more insights from various perspectives.
Outcome: The proposed model outperforms baselines and human evaluations on the extracted entities.
READoc: A Unified Benchmark for Realistic Document Structured Extraction (2025.findings-acl)

Copied to clipboard

Challenge: Document Structured Extraction (DSE) is a field of document structure analysis that aims to extract structured content from raw documents.
Approach: They propose a benchmark to evaluate document structured extraction systems by converting unstructured PDFs into semantically rich Markdown.
Outcome: The proposed benchmark is based on 3,576 diverse and real-world documents from arXiv, GitHub, and Zenodo.
Cost-effective End-to-end Information Extraction for Semi-structured Document Images (2021.emnlp-main)

Copied to clipboard

Challenge: a real-world information extraction system for semi-structured document images often involves a long pipeline of multiple modules, which can lead to unstable performance if not designed carefully.
Approach: They propose to use a sequence generation task to build an end-to-end IE system . they propose to combine three manually engineered modules with one data-driven module .
Outcome: The proposed system can be easily replaced and deployed in large-scale production.
Multi-modal Information Extraction from Text, Semi-structured, and Tabular Data on the Web (2020.acl-tutorials)

Copied to clipboard

Challenge: a tutorial explores the commonalities in the challenges and solutions developed to address information extraction from the World Wide Web.
Approach: This tutorial examines methods for extracting information from the World Wide Web . it explores the commonalities in the challenges and solutions developed to address these different forms of text .
Outcome: This paper examines the commonalities in the challenges and solutions developed to address the World Wide Web.
SciREX: A Challenge Dataset for Document-Level Information Extraction (2020.acl-main)

Copied to clipboard

Challenge: Conventional datasets and methods for information extraction focus on within-sentence relations from general Newswire text.
Approach: They propose a document-level IE dataset that integrates automatic and human annotations to annotate entities and document- level N-ary relation identification from scientific articles.
Outcome: The proposed dataset extends state-of-the-art IE models to document-level IE.
Document-level Entity-based Extraction as Template Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Document-level entity-based extraction (EE) tasks extract entity-centric information from unstructured text across multiple sentences.
Approach: They propose a generative framework for two document-level EE tasks: role-filler entity extraction (RE) and relation extraction ( RE).
Outcome: The proposed framework captures cross-entity dependencies and avoids exponential computation complexity of identifying N-ary relations.
NCRE: A Benchmark for Document-level Nominal Compound Relation Extraction (2025.coling-main)

Copied to clipboard

Challenge: Existing work focuses on detecting specific relations between entities, often constrained to specific fields and lacking general applicability.
Approach: They propose a novel task that concentrates on abstract relation extraction between noun phrases . they annotate a Chinese dataset and develop a model incorporating a rotary position-enhanced word pair detection schema.
Outcome: The proposed task is more efficient than previous methods.
A Domain-Specific Curated Benchmark for Entity and Document-Level Relation Extraction (2026.findings-eacl)

Copied to clipboard

Challenge: Existing biomedical IE benchmarks are narrow in scope and rely heavily on distantly supervised annotations.
Approach: They propose a benchmark for Information Extraction (IE) that annotates entities, concept-level links, and relations manually from PubMed abstracts.
Outcome: The GutBrainIE benchmark is based on more than 1,600 PubMed abstracts, manually annotated by biomedical and terminological experts with fine-grained entities, concept-level links, and relations.
Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for extracting structured procedural knowledge from unstructured business documents are limited by simplistic schemas and shallow logical dependencies.
Approach: They propose a framework for extracting structured procedural knowledge from unstructured business documents . they propose BREX, a carefully curated benchmark comprising 409 real-world business documents and 2,855 expert-annotated rules .
Outcome: The proposed framework outperforms standard prompts in rule extraction and execution.
PARSE: LLM Driven Schema Optimization for Reliable Entity Extraction (2025.emnlp-industry)

Copied to clipboard

Challenge: Structured information extraction from unstructured text is critical for Software 3.0 systems . current approaches to extract structured information from unstructed text are static contracts .
Approach: They propose a system that automates JSON schemas for LLM consumption and optimizes them for LRM consumption.
Outcome: The proposed system improves extraction accuracy and reduces errors by 92% within the first retry and maintaining practical latency.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations