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.
PrivComp-KG : Leveraging Knowledge Graph and Large Language Models for Privacy Policy Compliance Verification
University of Texas at El Paso(德克萨斯大学埃尔帕索分校);Texas A&M University Central Texas(德克萨斯农工大学中央德克萨斯分校);University of Maryland Baltimore County(马里兰大学巴尔的摩县分校)
Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy
Digital Transit Limited, 3M Buckley Innovation Centre(数字交通有限公司,3M Buckley创新中心);Department of Computer Science at University of Huddersfield(赫德瑟尔大学计算机科学系)
University of Arizona(亚利桑那大学);Avirtek, Inc.(Avirtek公司);Joint Interoperability Test Command (JITC), United States Department of Defense(美国国防部联合互操作性测试司令部)
Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II
Technichal University Berlin XpaliNLP Group(柏林工业大学 XpaliNLP 组);Research Center for Artificial Intelligence (DFKI)(人工智能研究中心(DFKI));Center for European Research on Trusted AI (CERTAIN)(欧洲可信人工智能研究中心(CERTAIN))
Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces
School of Mechanical, Aerospace, and Manufacturing Engineering(机械、航空航天与制造工程学院);University of Connecticut(康涅狄格大学);Department of Computer Science(计算机科学系);University of California Irvine(加州大学欧文分校)
Assessing High-Risk AI Systems under the EU AI Act: From Legal Requirements to Technical Verification
Luxembourg Institute of Science and Technology (LIST)(卢森堡科学技术研究院(LIST));LIST, University of Luxembourg(卢森堡大学LIST);Research Institutes of Sweden (RISE)(瑞典研究院(RISE))
ARCEAK: An Automated Rule Checking Framework Enhanced with Architectural Knowledge
Shanghai Jiao Tong University(上海交通大学);Beijing University of Civil Engineering and Architecture(北京建筑大学);East China Architectural Design & Research Institute(华东建筑设计研究院)