审计和财务分析从业者终于有了一个专门评估 LLM 识别财务造假的基准——AuditFraudBench 直击现有模型在误导性披露和欺诈模式上的短板，做金融 NLP 或审计自动化的团队值得用它来检验自己的模型。
现有金融审计基准主要关注事实验证和规则合规，但缺乏对误导性披露叙述的评估。研究者推出 AuditFraudBench，基于真实公司文件和监管材料构建，包含利润来源归因、误导性叙述检测和欺诈模式分类三个任务。测试 GPT、DeepSeek、Qwen 等模型发现，无论是闭源还是开源模型，在联合推理财务数据、披露框架、重述证据和执法欺诈机制方面仍表现不佳。该基准为评估 LLM 在财务报告中的审计相关能力提供了具有挑战性的测试平台。
AuditFraudBench: Benchmarking Audit Judgment in Detecting Fraudulent Misstatements
Large language models (LLMs) have shown strong performance in financial analysis and surface-level factual error detection, yet their ability to identify fraudulent financial misinformation in audited corporate reporting remains underexplored. Existing financial and audit benchmarks mainly focus on factual verification, numerical reasoning, rule compliance, or audit workflows, but rarely evaluate misleading disclosure narratives or management explanations that obscure the true drivers of reported performance. We introduce AuditFraudBench, an enforcement-grounded benchmark constructed from authentic company filings and regulatory materials, including original and restated 10-K and 10-Q filings, structured financial statements, MD&A disclosures, and SEC Accounting and Auditing Enforcement Releases (AAERs). AuditFraudBench contains three tasks: Profit Source Attribution, Misleading Narrative Detection, and Fraud Pattern Classification, which evaluate whether models can identify the true source of reported performance, detect misleading disclosure framing, and classify misconduct mechanisms into known manipulation patterns. We evaluate GPT, DeepSeek, and Qwen series LLMs on the benchmark. Results show that both proprietary and open models still struggle to jointly reason over financial figures, disclosure framing, restatement evidence, and enforcement-grounded fraud mechanisms. AuditFraudBench provides a challenging testbed for audit-relevant, evidence-grounded evaluation of LLMs in financial reporting.