VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings· VERA-8B：基于 SEC 文件的证据支持审计风险推理
Across audit applications, judgments must be supported by reasonable evidence. However, standard financial language models prioritize fluency over evidence. They are built for general financial reasoning and may produce plausible but ambiguous answers, creating a grounding gap that makes them unsuitable for audit work. We address this gap with VERA-8B, a new end-to-end audit reasoning system that identifies audit risks before enforcement actions occur. Constructing such a model raises several challenges, as no prior machine learning work targets pre-enforcement audit prediction. To our knowledge, we are the first to unify SFT and GRPO for evidence-grounded audit reasoning under one evidence standard, achieving performance that surpasses all evaluated baselines. Because auditing cannot tole
VERA-8B 通过结合 SFT 和 GRPO 方法，基于 SEC 文件提供证据支持的审计风险预测。
- 核心方法
- VERA-8B 使用了一种新的端到端审计推理系统，结合了监督细调（SFT）和基于检索的生成预训练（GRPO）方法，以 SEC 文件为证据标准，实现审计风险的准确预测。
- 适合谁读
- 研究者、工程师、审计从业人员
- 要解决的问题
- 现有的金融语言模型在进行审计推理时，过度关注流畅性而忽视证据支持，导致其答案可能含糊不清，不适用于审计工作。
- 关键实验
- 关键实验包括使用 SEC 文件数据集对模型进行训练和评估，展示了 VERA-8B 在审计风险预测上的优越性能。
- 主要贡献
- 首次将 SFT 和 GRPO 统一在同一个模型中，用于基于证据的审计风险推理，性能超过所有评估的基线模型。
- 意义与局限
- VERA-8B 为审计行业提供了一种更加可靠和准确的风险预测工具，有助于提前发现潜在的违规行为。然而，模型的复杂性和数据依赖性可能限制其在资源有限环境中的应用。