LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing
2026-08-17 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed LAVA, a system to check financial documents like paychecks and tax forms with high accuracy. It uses advanced language models to handle different document layouts and complex rules by breaking the task into four steps: finding rules, extracting information while keeping the document’s structure, adding extra details, and verifying everything with clear checks. Tested on many real financial documents, LAVA was better at avoiding mistakes and handling tricky cases compared to existing methods. This makes it useful for careful and fast financial validations.
Financial document validationPayroll auditingTax complianceLoan underwritingMultimodal large language modelsInformation extractionRule-based verificationError attributionSymbolic verificationDocument layout analysis
Authors
Ruoqi Shu, Xuhui Wang, Isaac Wang, Yanming Mai, Bo Wan
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.