用符号环境提升大模型对财务报告的审计准确性。
AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification
- 构建基于税则图谱与财报图谱的符号化审计环境，分离搜索与验证。
- 在金融审计数据集上达成82.09%联合审计准确率，优于基线14.93点。
- 适合需高可信度审计验证的财务、监管及AI系统开发者。
结构化财务审计验证对语言模型代理而言困难，因正确性依赖结构化证据而非文本本身。模型必须将报告事实关联到税则概念，遍历计算或维度关系，并重新计算预期值后应用审计规则。我们提出AuditFlow，一种基于图的多智能体框架，将自适应搜索与确定性验证分离。AuditFlow从静态美国通用会计准则（US-GAAP）税则图谱和动态XBRL申报图谱构建符号环境，通过类型化工具提供事实检索、税则遍历、数值校验与规则评估功能。两名初级审计员分别从监管和证据视角审查案例，资深审计员协调分歧并可发起进一步调查。最终报告通过证据聚合生成审计结论、预期值、证据链与可信度评分。在基于FinAuditing的FinMR样本上，AuditFlow在GPT-5.5下达到82.09%联合审计准确率，比最强基线高出14.93个百分点。移除确定性检查后准确率降至17.91%，表明符号环境完成了模型无法可靠替代的验证步骤。
原文摘要 · Abstract (English)
Structured financial audit verification is difficult for language-model agents because correctness depends on structured evidence rather than text alone. A model must link reported facts to taxonomy concepts, traverse calculation or dimensional relations, and recompute expected values before applying an audit rule. We propose AuditFlow, a graph-grounded multi-agent framework that separates adaptive search from deterministic verification. AuditFlow builds a symbolic environment from a static US-GAAP taxonomy graph and a dynamic XBRL filing graph, and exposes it through typed tools for fact retrieval, taxonomy traversal, numerical checking, and rule evaluation. Two junior auditors inspect each case from regulatory and evidentiary views, while a senior auditor resolves disagreements and can request further investigation. The final reports are fused through evidential aggregation to produce an audit verdict, expected value, evidence trail, and trustworthiness score. On a FinAuditing-derived FinMR sample, AuditFlow reaches 82.09% joint audit accuracy under GPT-5.5, outperforming the strongest baseline by 14.93 points. Removing deterministic checks drops accuracy to 17.91%, showing that the symbolic environment performs the verification step that the model cannot reliably replace.
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。