Challenge: Structured information extraction from long, multilingual scanned financial documents is a core requirement in industrial KYC and compliance workflows.
Approach: They propose a framework for structured information extraction from long, multilingual scanned financial documents . they combine image preprocessing, multilinguistic OCR, hybrid page-level retrieval and VLMs .
Outcome: The proposed pipeline outperforms direct PDF-to-VLM baselines on 120 production KYC documents.

Similar Papers

OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets (2026.eacl-industry)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) are used for document information extraction, but their impact on document information processing remains unclear.
Approach: They propose an automated hierarchical error analysis framework that leverages large language models to diagnose errors systematically.
Outcome: The proposed framework can achieve comparable performance to OCR-enhanced approaches.
MultiDocFusion : Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents (2025.emnlp-main)

Copied to clipboard

Challenge: Existing text chunking methods neglect complex and long industrial document structures, causing information loss and reduced answer quality.
Approach: They propose a multimodal chunking pipeline that detects document regions and extracts text from them via OCR.
Outcome: Extensive tests show that MultiDocFusion improves retrieval precision by 8–15% and ANLS QA scores by 2–3% compared to baselines.
Synthesizing question answering data from financial documents: An End-to-End Multi-Agent Approach (2026.eacl-industry)

Copied to clipboard

Challenge: Large language models excel at financial reasoning but their deployment for enterprise use cases remains costly and often constrained by latency, privacy, and regulatory requirements.
Approach: They propose a pipeline that extracts and selects relevant content from unstructured financial documents and generates QA pairs from the selected content for SLM fine-tuning.
Outcome: The proposed model outperforms models trained on previous manual models and achieves competitive in-distribution performance.
A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends (2026.findings-acl)

Copied to clipboard

Challenge: Visually Rich Document Understanding (VRDU) frameworks are a key area of research . early approaches to VRDU relied on manually crafted rules and domain-specific heuristics . conventional deep learning approaches do not integrate the diverse modalities in documents .
Approach: They review recent advances in MLLM-based Visually Rich Document Understanding (VRDU) their findings highlight emerging trends and promising research directions .
Outcome: The proposed frameworks are scalable, reliable, and adaptable, the authors argue . their findings highlight emerging trends and promising research directions .
A Multilingual Information Extraction Pipeline for Investigative Journalism (D18-2)

Copied to clipboard

Challenge: a new pipeline is being developed to process large collections of unstructured textual data . the pipeline is a key input processor for the upcoming major release of our software .
Approach: a new pipeline is introduced to extract large amounts of unstructured data . the pipeline is used by journalists to process large files containing unknown contents .
Outcome: the pipeline is an input processor for the upcoming major release of our new/s/leak 2.0 software.
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world .
Approach: They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions.
Outcome: The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents.
LMDX: Language Model-based Document Information Extraction and Localization (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models have revolutionized Natural Language Processing but their application in extracting information from visually rich documents has not been successful.
Approach: They propose a language model-based document information extraction and localization methodology to reframe the document information extract task for a LLM.
Outcome: The proposed method enables extraction of singular, repeated, and hierarchical entities with and without training data.
Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training (2026.findings-eacl)

Copied to clipboard

Challenge: Existing open-source datasets predominantly apply a single fixed extractor to all webpages.
Approach: They propose to take a Union over different extractors to improve model performance . they show that extractor choice can significantly impact downstream task performance based on content type .
Outcome: The proposed approach can increase the token yield of DCLM-Baseline by 71% while maintaining benchmark performance.
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.

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