LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

• URL: http://arxiv.org/abs/2608.16763v1
• Date: Mon, 17 Aug 2026 16:10:05 GMT
• Title: LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing
• Abstract summary: LAVA is a modular, backbone-agnostic pipeline built on multimodal large language models.<n>It integrates document-rule retrieval, layout-preserving information extraction, auxiliary metadata enrichment, and auditable symbolic/arithmetic verification.<n>It supports robust rule grounding, fine-grained error attribution, and consistent, traceable end-to-end execution capabilities.
• Score: 8.198653897327864
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process reliably. We introduce LAVA (Logic-Aware Validation and Augmentation), a modular, backbone-agnostic pipeline built on multimodal large language models, that integrates a four-stage design: document-rule retrieval, layout-preserving information extraction, auxiliary metadata enrichment, and auditable symbolic/arithmetic verification. LAVA supports robust rule grounding, fine-grained error attribution, and consistent, traceable end-to-end execution, capabilities essential for high-stakes deployment. Evaluated on a large real-world benchmark with diverse financial documents and dozens of expert-curated validation rules, LAVA outperforms baselines in hallucination control and edge-case handling while maintaining efficient token usage, demonstrating practicality for high-volume, time-critical validation.

Related papers

• DECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods [2.0789144738685956]
  This paper introduces DECODEM, a set of benchmark datasets for evaluating the automated extraction of corporate governance variables from organizational documents.<n>The benchmarks pair randomly sampled corporate charters and bylaws with high-quality human annotations covering a range of governance provisions commonly studied in empirical work.<n>The results show that automated extraction is feasible at a high level of accuracy for many provisions, with median performance near the upper bound across approaches.
  arXiv  Detail & Related papers  (2026-07-17T11:48:31Z)
• Retrieval-Augmented Reasoning for Chartered Accountancy [0.08749675983608168]
  We present CA-ThinkFlow as a parameter-efficient Retrieval-Augmented Generation framework.<n>The framework shows high efficiency and strength in handling parameters, but essential reasoning abilities fail to process complex regulatory texts.
  arXiv  Detail & Related papers  (2026-04-30T21:50:49Z)
• Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models [53.279391576560755]
  Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and limitation.<n>This poses significant risks in high-stakes domains such as healthcare, law, and scientific communication, where trust and verifiability are paramount.<n>We introduce DAVinCI - a Dual Attribution and Verification framework designed to enhance the factual reliability and interpretability of LLM outputs.
  arXiv  Detail & Related papers  (2026-04-23T01:37:50Z)
• Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems [9.927850680621038]
  We present the design of a real-time verification component integrated into a production RAG pipeline.<n>The system processes documents up to 32K tokens and employs adaptive inference strategies to balance response time and verification coverage.
  arXiv  Detail & Related papers  (2026-03-04T12:53:21Z)
• IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation [49.796717294455796]
  We present IMMACULATE, a practical auditing framework that detects economically motivated deviations.<n>IMMACULATE selectively audits a small fraction of requests using verifiable computation, achieving strong detection guarantees while amortizing cryptographic overhead.
  arXiv  Detail & Related papers  (2026-02-26T07:21:02Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• 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)
• Large Language Model-Driven Code Compliance Checking in Building Information Modeling [3.2648052741820166]
  This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling.<n>It introduces a Large Language Model (LLM)-driven approach to semi-automate this critical process.<n>The developed system integrates LLMs such as GPT, Claude, Gemini, and Llama, with Revit software to interpret building codes, generate Python scripts, and perform semi-automated compliance checks.
  arXiv  Detail & Related papers  (2025-06-25T15:50:34Z)
• An Efficient Deep Learning-Based Approach to Automating Invoice Document Validation [0.0]
  We propose to automate the validation of machine written invoices using document layout analysis and object detection techniques.<n>We introduce a novel dataset consisting of manually annotated real-world invoices and a multi-criteria validation process.
  arXiv  Detail & Related papers  (2025-03-15T21:33:00Z)
• OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs [59.836774258359945]
  OpenFactCheck is a framework for building customized automatic fact-checking systems.<n>It allows users to easily customize an automatic fact-checker and verify the factual correctness of documents and claims.<n>CheckerEVAL is a solution for gauging the reliability of automatic fact-checkers' verification results using human-annotated datasets.
  arXiv  Detail & Related papers  (2024-05-09T07:15:19Z)
• Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers [121.53749383203792]
  We present a holistic end-to-end solution for annotating the factuality of large language models (LLMs)-generated responses. We construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document. Preliminary experiments show that FacTool, FactScore and Perplexity are struggling to identify false claims.
  arXiv  Detail & Related papers  (2023-11-15T14:41:57Z)

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.