用AI精准审计财务文档，防错防幻觉，适合高要求企业场景
LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing
- 基于多模态大模型构建四阶段流水线，融合规则检索与符号验证
- 在真实数据集上有效降低幻觉率，处理复杂边缘案例表现优异
- 支持可追溯审计，适合金融、税务等高可靠性要求的场景
生产环境中的财务文档验证（如薪酬审计、税务合规、贷款授信）需在严格的企业约束下实现极高的准确性、一致性和可复现性。实际中，文档格式多样、语义丰富且依赖上下文，嵌入的业务规则使现有流程难以可靠处理。我们提出LAVA（Logic-Aware Validation and Augmentation），一个模块化、与主干模型无关的多模态大模型框架，采用四阶段设计：文档-规则检索、布局保持的信息提取、辅助元数据增强、可审计的符号/算术验证。LAVA支持强规则对齐、细粒度错误归因和一致可追溯的端到端执行，满足高风险部署需求。在包含多样化财务文档和数十条专家定制验证规则的真实世界大规模基准上评估，LAVA在幻觉控制和边缘情况处理上优于基线方法，同时保持高效令牌使用，验证了其在高吞吐、高时效场景下的实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。