arXiv：cs.CL· Florentina Voboril·· 6 小时前
基于 LLM 的贷款申请政策合规验证
LLM-Based Policy Compliance Verification of Loan Applications
AI 导读
一项研究提出了基于 LLM 的贷款申请政策合规检查器原型，采用两步架构：先从政策文档中自动提取合规规则并转为机器可读表示，再据此评估贷款申请，识别政策例外、不合规项、缺失信息及需人工复核的案例。
正文
Abstract:Banks rely on extensive internal policy frameworks to ensure that corporate lending decisions comply with regulatory requirements and internal risk standards. Reviewing loan applications against these policies is a largely manual and knowledge-intensive process, which can lead to overlooked policy violations or exceptions. This report presents a prototype of an LLM-based policy checker that automatically verifies loan applications against internal lending policies.
The proposed approach follows a two-step architecture. First, compliance-relevant rules are automatically extracted from policy documents and converted into structured, machine-readable representations. Second, loan applications are evaluated against the extracted rules to identify policy exceptions, non-compliant findings, missing information, and cases requiring manual review.
Evaluation results demonstrate that the rule extraction process is highly stable across multiple runs and consistently captures rules identified as critical by a domain expert. When evaluated on 11 real loan applications with known policy exceptions, the system successfully detected the majority of these exceptions and identified additional compliance issues that had previously been overlooked during manual reviews. While the approach produces false positives and cannot fully replace human judgement, the results indicate that LLM-based policy compliance verification can provide valuable support in the loan application verification process by highlighting potential compliance risks.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.20155 [cs.AI] |
| (or arXiv:2610.20155v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20155 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Florentina Voboril [view email]
[v1]
Wed, 14 Oct 2026 13:12:51 UTC (62 KB)
来源：arXiv：cs.CL · arxiv.org