Agentar-Fin-OCR

• URL: http://arxiv.org/abs/2603.11044v1
• Date: Wed, 11 Mar 2026 17:59:42 GMT
• Title: Agentar-Fin-OCR
• Abstract summary: Agentar-Fin-OCR is a document parsing system tailored to financial-domain documents.<n>To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, Agentar-Fin-OCR combines a Cross-page Contents Consolidation algorithm.<n>Experiments demonstrate that our model shows high performance on the table parsing metrics of OmniDocBench.
• Score: 6.212573253529528
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose Agentar-Fin-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, Agentar-Fin-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of Contents (TOC) tree for structure-aware retrieval, and (2) a difficulty-adaptive curriculum learning training strategy for table parsing, together with a CellBBoxRegressor module that uses structural anchor tokens to localize table cells from decoder hidden states without external detectors. Experiments demonstrate that our model shows high performance on the table parsing metrics of OmniDocBench. To enable realistic evaluation in the financial vertical, we further introduce FinDocBench, a benchmark that includes six financial document categories with expert-verified annotations and evaluation metrics including Table of Contents edit-distance-based similarity (TocEDS), cross-page concatenated TEDS, and Table Cell Intersection over Union (C-IoU). We evaluate a wide range of state-of-the-art models on FinDocBench to assess their capabilities and remaining limitations on financial documents. Overall, Agentar-Fin-OCR and FinDocBench provide a practical foundation for reliable downstream financial document applications.

Related papers

• FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks [35.14324618292104]
  FinixDoc is an end-to-end agentic parsing system for real-world financial documents.<n>We present FinixDocVL, a 4Bscale vision model built on Qwen3-VL-4B as its core.<n>For evaluation, we construct FinixDocBench, a financial-domain evaluation suite covering digital-native, camera-captured, ultra-large-page, and internal-workflow scenarios.
  arXiv  Detail & Related papers  (2026-08-24T06:20:18Z)
• Hierarchical Reranking for Scalable Financial RAG System [4.690968174645844]
  We propose Hierarchical Reranker, a RAG framework designed to improve retrieval performance and generative reliability across large-scale financial datasets.<n>The proposed system achieved an NDCG@20 score of 0.7918 and demonstrated superior factual consistency.<n>This work presents a deployable, domain-optimized RAG pipeline that enhances both the accuracy and scalability of financial reasoning.
  arXiv  Detail & Related papers  (2026-07-29T23:25:45Z)
• FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR Evaluation [45.16693985619424]
  FinCriticalED is a visual benchmark for evaluating OCR and vision language models on financial documents at the fact level.<n>FinCriticalED provides 500 image- HTML pairs with expert annotated financial facts covering over seven hundred numerical and temporal facts.
  arXiv  Detail & Related papers  (2025-11-19T00:41:14Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• FinSight: Towards Real-World Financial Deep Research [68.31086471310773]
  FinSight is a novel framework for producing high-quality, multimodal financial reports.<n>To ensure professional-grade visualization, we propose an Iterative Vision-Enhanced Mechanism.<n>A two-stage Writing Framework expands concise Chain-of-Analysis segments into coherent, citation-aware, and multimodal reports.
  arXiv  Detail & Related papers  (2025-10-19T14:05:35Z)
• Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding [61.36285696607487]
  Document understanding is critical for applications from financial analysis to scientific discovery.<n>Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs) face key limitations.<n>Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG.
  arXiv  Detail & Related papers  (2025-10-17T02:33:16Z)
• FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs [40.216867348210265]
  FinAuditing is the first taxonomy-aligned, structure-aware, multi-document benchmark for evaluating financial auditing tasks.<n>Built from real US-compliant.<n> filings, FinAuditing defines three complementary subtasks, FinSM for semantic consistency, FinRE for relational consistency, and FinMR for numerical consistency.<n>Extensive zero-shot experiments on 13 state-of-the-art LLMs reveal that current models perform inconsistently across semantic, relational, and mathematical dimensions.
  arXiv  Detail & Related papers  (2025-10-10T00:41:55Z)
• FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering [57.18367828883773]
  FinAgentBench is a benchmark for evaluating agentic retrieval with multi-step reasoning in finance.<n>The benchmark consists of 26K expert-annotated examples on S&P-500 listed firms.<n>We evaluate a suite of state-of-the-art models and demonstrate how targeted fine-tuning can significantly improve agentic retrieval performance.
  arXiv  Detail & Related papers  (2025-08-07T22:15:22Z)
• MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks [56.350173737493215]
  Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency.<n>MMESGBench is a first-of-its-kind benchmark dataset to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents.<n>MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories.
  arXiv  Detail & Related papers  (2025-07-25T03:58:07Z)
• Structuring the Unstructured: A Multi-Agent System for Extracting and Querying Financial KPIs and Guidance [54.25184684077833]
  We propose an efficient and scalable method for extracting quantitative insights from unstructured financial documents.<n>Our proposed system consists of two specialized agents: the emphExtraction Agent and the emphText-to-Agent
  arXiv  Detail & Related papers  (2025-05-25T15:45:46Z)
• ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents [0.0]
  The paper presents an approach to adapt a multimodal transformer (i.e., ViBERTgrid) for unstructured financial documents, by incorporating a BiLSTM-CRF layer. The proposed ViBERTgrid BiLSTM-CRF model demonstrates a significant improvement in performance (up to 2 percentage points) on named entity recognition from unstructured documents in financial domain.
  arXiv  Detail & Related papers  (2024-09-23T13:28:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.