用神经符号策略验证金融AI推理，解决计算错误与合规问题
VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation
- 融合密集检索与交叉编码重排序，加入金融工具代理和自动化推理策略
- 在FinanceBench上事实正确率从52.4%提升至94.7%，相对提升81%
- 专攻数学与逻辑错误，适合需高精度的金融合规与投资决策场景
金融AI系统存在关键盲点：尽管检索增强生成（RAG）能精准找文档，语言模型在推理中仍会产生计算错误和监管违规，即使检索完美。本文提出VERAFI（经验证的智能金融代理），一种结合神经符号策略生成的智能体框架，实现可信金融智能。VERAFI融合前沿密集检索与交叉编码重排序，搭配金融工具支持的智能体及覆盖GAAP合规、SEC要求与数学验证的自动推理策略。在FinanceBench上的全面评估显示：传统密集检索加重排序仅达52.4%事实正确率，而VERAFI集成方法提升至94.7%，相对提高81%。神经符号策略层单独贡献4.3个百分点提升，专门针对持续存在的数学与逻辑错误。通过将金融领域知识直接嵌入推理过程，VERAFI为满足监管合规、投资决策与风险管理的严苛准确需求，提供了可落地的可信金融AI路径。
原文摘要 · Abstract (English)
Financial AI systems suffer from a critical blind spot: while Retrieval-Augmented Generation (RAG) excels at finding relevant documents, language models still generate calculation errors and regulatory violations during reasoning, even with perfect retrieval. This paper introduces VERAFI (Verified Agentic Financial Intelligence), an agentic framework with neurosymbolic policy generation for verified financial intelligence. VERAFI combines state-of-the-art dense retrieval and cross-encoder reranking with financial tool-enabled agents and automated reasoning policies covering GAAP compliance, SEC requirements, and mathematical validation. Our comprehensive evaluation on FinanceBench demonstrates remarkable improvements: while traditional dense retrieval with reranking achieves only 52.4\% factual correctness, VERAFI's integrated approach reaches 94.7\%, an 81\% relative improvement. The neurosymbolic policy layer alone contributes a 4.3 percentage point gain over pure agentic processing, specifically targeting persistent mathematical and logical errors. By integrating financial domain expertise directly into the reasoning process, VERAFI offers a practical pathway toward trustworthy financial AI that meets the stringent accuracy demands of regulatory compliance, investment decisions, and risk management.
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。