VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings
Artificial Intelligence
Summary
The authors created VERA-8B, a new system designed to help auditors find financial risks before any enforcement actions happen. Unlike usual financial language models that focus on sounding fluent, VERA-8B makes sure its answers are backed by solid evidence, which is critical for auditing. They combined two training approaches and introduced ways for the system to avoid guessing when uncertain. Additionally, they built AuditBridge to turn raw financial data into clear reports for auditors to review easily.
Authors
Menghan Liu, Elynn Chen
Abstract
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 tolerate unsupported claims, we introduce abstention and uncertainty qualification to defer uncertain or evidence-incomplete cases. Finally, we design an AuditBridge to ground model reasoning for practical audit work. It transforms raw filings into verified records and then into reviewer-ready reports, bridging finance and computation with broad generality. Together, these components produce auditable, review-ready outputs suitable for practical audit work.