Document-Level Numerical Reasoning across Single and Multiple Tables in Financial Reports

• URL: http://arxiv.org/abs/2604.03664v1
• Date: Sat, 04 Apr 2026 09:30:59 GMT
• Title: Document-Level Numerical Reasoning across Single and Multiple Tables in Financial Reports
• Abstract summary: FinLongDocQA is a dataset for both single-table and cross-table financial numerical reasoning in long-context reports.<n>We propose FinLongDocAgent, a Multi-Agent Multi-Round Retrieval-Augmented Generation that iteratively retrieves evidence, performs intermediate calculations, and verifies results across rounds.
• Score: 18.557627180602164
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Despite the strong language understanding abilities of large language models (LLMs), they still struggle with reliable question answering (QA) over long, structured documents, particularly for numerical reasoning. Financial annual reports exemplify this difficulty: financial statement analysis often hinges on accurate arithmetic, and analysts derive key indicators by integrating evidence scattered across multiple tables and narrative text. However, existing benchmarks focus largely on single-table settings, leaving cross-table document-level numerical reasoning underexplored. To address this gap, we introduce FinLongDocQA, a dataset for both single-table and cross-table financial numerical reasoning in long-context reports. Evaluating both closed-source and open-source LLMs on FinLongDocQA reveals two bottlenecks: (1) annual reports often exceed 129k tokens, exacerbating the context rot problem for locating relevant tables; and (2) even when relevant evidence is located, LLMs remain prone to errors in multi-step numerical reasoning. We propose FinLongDocAgent, a Multi-Agent Multi-Round Retrieval-Augmented Generation (RAG) approach that iteratively retrieves evidence, performs intermediate calculations, and verifies results across rounds. Experiments highlight the importance of iterative retrieval and verification for reliable numerical QA in long financial documents.

Related papers

• Beyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting [0.0]
  Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents.<n>We propose a two-phase non-parametric retrieval architecture that separates high-recall candidate retrieval from high-precision utility ranking.<n>In production deployment across more than 800 credit analysts, document review time was reduced from several hours to approximately three minutes.
  arXiv  Detail & Related papers  (2026-05-20T04:23:06Z)
• When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents [3.4992819560032267]
  Vision-language models (VLMs) perform well on many document understanding tasks, yet their reliability in specialized, non-English domains remains underexplored.<n>We introduce Multimodal Finance Eval, the first multimodal benchmark for evaluating French financial document understanding.<n>The dataset contains 1,204 expert-validated questions spanning text extraction, table comprehension, chart interpretation, and multi-turn conversational reasoning.
  arXiv  Detail & Related papers  (2026-02-11T00:04:56Z)
• Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings [31.87459935714186]
  Fin-RATE is a benchmark built on U.S. Securities and Exchange Commission (SEC) filings and mirroring financial analyst.<n>We benchmark 17 leading Large Language Models (LLMs) across open-source, closed-source, and finance-specialized models.<n>Results show substantial performance degradation, with accuracy dropping by 18.60% and 14.35% as tasks shift from single-document reasoning to longitudinal and cross-entity analysis.
  arXiv  Detail & Related papers  (2026-02-07T00:54:37Z)
• Structure First, Reason Next: Enhancing a Large Language Model using Knowledge Graph for Numerical Reasoning in Financial Documents [0.21485350418225244]
  Large Language Models (LLMs) have shown promising results in multiple Question-Answering (Q-A) systems.<n>Structured data augmentations, such as Knowledge Graphs (KGs), have notably improved the predictions of LLMs.<n>This paper proposes a framework to incorporate structured information using KGs along with LLM predictions for numerical reasoning tasks.
  arXiv  Detail & Related papers  (2026-01-12T17:39:08Z)
• LongDA: Benchmarking LLM Agents for Long-Document Data Analysis [55.32211515932351]
  LongDA targets real-world settings in which navigating long documentation and complex data is the primary bottleneck.<n>LongTA is a tool-augmented agent framework that enables document access, retrieval, and code execution.<n>Our experiments reveal substantial performance gaps even among state-of-the-art models.
  arXiv  Detail & Related papers  (2026-01-05T23:23:16Z)
• 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)
• FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering [57.43420753842626]
  FinLFQA is a benchmark designed to evaluate the ability of Large Language Models to generate long-form answers to complex financial questions.<n>We provide an automatic evaluation framework covering both answer quality and attribution quality.
  arXiv  Detail & Related papers  (2025-10-07T20:06:15Z)
• 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)
• MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application [118.63802040274999]
  MultiFinBen is the first expert-annotated multilingual (five languages) and multimodal benchmark for evaluating LLMs in realistic financial contexts.<n>Financial reasoning tests cross-lingual evidence integration from filings and news, and financial OCR, which extracts structured text from scanned documents.<n> evaluating 21 leading LLMs shows that even frontier multimodal models like GPT-4o achieve only 46.01% overall, stronger on vision and audio but dropping sharply in multilingual settings.
  arXiv  Detail & Related papers  (2025-06-16T22:01:49Z)
• SEC-QA: A Systematic Evaluation Corpus for Financial QA [12.279234447220155]
  Existing datasets are often constrained by size, context, or relevance to practical applications. We propose SEC-QA, a continuous dataset generation framework with two key features. We introduce a QA system based on program-of-thought that improves the ability to perform complex information retrieval and quantitative reasoning pipelines.
  arXiv  Detail & Related papers  (2024-06-20T15:12:41Z)

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.