发表机构
OCBC（华侨银行）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种分解置信度层（感知、布局、验证）结合一致性风险控制，显著提升金融文档直通处理的校准可靠性，使自动批准率从0.1%-7.0%提升至49-72%。
AI 中文摘要
在无需人工审核的情况下，对从金融文档中提取的键值对进行直通处理（STP），需要校准的概率以及自动批准层级残差的有限保证。现代视觉语言模型（VLM）的出现提供了开箱即用的键值提取能力，但其口头化的置信度信号不可靠，且对字段正确性的追踪能力较弱。本文引入了一个分解置信度层，沿感知、布局和验证三个可解释通道展开。结合最终的一致性风险控制，该分数可用于金融文档的可靠直通处理。该方法在三个公共数据集上进行了验证，涵盖真实发票、合成发票和广告购买表单，使用了两个不同的VLM系列（Qwen3.6-27B和Gemini-3.1-Flash-Lite）。我们的分解分数持续改善了正确与错误提取的分离，将VLM口头化信号的AUROC从0.54-0.74大幅提升至0.90-0.99，且三个设计通道均有贡献。对工业部署至关重要的一点是，这实现了可用的直通处理。原生VLM置信度信号在目标错误率<10%的风险控制下仅能清除0.1%-7.0%的字段。相比之下，所提出的方法自动批准了49-72%的字段，同时将接受层的经验错误率保持在目标值或以下。
英文摘要
Straight-through processing (STP) on extracted key-value fields from financial documents without human review requires a calibrated probability together with a bounded guarantee on the residual error of the auto-approved tier. The emergence of modern Vision Language Models (VLMs) provides an out-of-the-box capability for extracting the key-values, but their verbalized confidence signals are unreliable and weakly track field correctness. This paper introduces a decomposed confidence layer along three interpretable channels, including perception, layout, and validation. Together with a final conformal risk control, the score can be used for reliable STP of financial documents. The method is validated on three public datasets covering real invoices, synthetic invoices, and ad-buy forms, using two different VLM families (Qwen3.6-27B and Gemini-3.1-Flash-Lite). Our decomposed score consistently improves the separation of correct from incorrect extractions, substantially raising the AUROC from 0.54-0.74 for VLM verbalized signals to 0.90-0.99 with contributions from all three designed channels. Crucially for industrial deployment, this enables usable STP. The native VLM confidence signals could clear only 0.1%-7.0% of fields under risk control at a target error of <10%. In contrast, the proposed method auto-approves 49-72% of fields while holding the empirical error of the accepted tier at or below the target.
