用大模型+逻辑求解器自动分析金融合规，让系统自己纠错并保证合法。
Neuro-Symbolic Compliance: Integrating LLMs and SMT Solvers for Automated Financial Legal Analysis
- 大模型解析法规生成逻辑约束，求解器验证一致性并找最小修改方案。
- 在87个台湾案例中正确生成SMT代码达86.2%，推理速度提升100倍以上。
- 适合需要严格合规与可验证推理的金融监管、法律科技场景。
金融监管规则日益复杂，阻碍了自动化合规，尤其难以在极少人工干预下维持逻辑一致性。我们提出一种神经符号合规框架，将大语言模型（LLMs）与满足度模理论（SMT）求解器结合，实现形式化可验证与基于优化的合规修正。LLM解读法规与执法案例以生成SMT约束，求解器则确保一致性，并在触发处罚时计算恢复合法性所需的最小事实修改。相比注重透明度的方法，本方法强调基于逻辑的优化，提供可验证且符合法律的推理，而非事后解释。在台湾金融监督管理委员会（FSC）的87个执法案例上评估，系统在SMT代码生成上达到86.2%正确率，推理效率提升超100倍，且持续纠正违规行为，初步建立了基于优化的合规应用基础。
原文摘要 · Abstract (English)
Financial regulations are increasingly complex, hindering automated compliance-especially the maintenance of logical consistency with minimal human oversight. We introduce a Neuro-Symbolic Compliance Framework that integrates Large Language Models (LLMs) with Satisfiability Modulo Theories (SMT) solvers to enable formal verifiability and optimization-based compliance correction. The LLM interprets statutes and enforcement cases to generate SMT constraints, while the solver enforces consistency and computes the minimal factual modification required to restore legality when penalties arise. Unlike transparency-oriented methods, our approach emphasizes logic-driven optimization, delivering verifiable, legally consistent reasoning rather than post-hoc explanation. Evaluated on 87 enforcement cases from Taiwan's Financial Supervisory Commission (FSC), the system attains 86.2% correctness in SMT code generation, improves reasoning efficiency by over 100x, and consistently corrects violations-establishing a preliminary foundation for optimization-based compliance applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。