用符号逻辑+大模型实现企业政策合规审查的可解释化
PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines
- 将企业政策转化为可执行的逻辑规则与原子问题
- 大模型回答局部问题，符号引擎判断是否违规
- 适合需要可审计合规审查的企业场景
基于政策的文档审查需判断目标文档是否符合组织特定政策、指南或操作手册。尽管大语言模型可辅助政策解读和文档分析，但端到端提示方法使政策逻辑隐含，导致合规决策难以审查、更新与测试。我们提出 PolicyGuard，一种神经符号框架，用于基于政策的文档合规审查。PolicyGuard 将组织政策转化为包含类型化关系逻辑规则和原子级提取问题的可执行审查引擎。审查过程中，大模型利用检索到的文档证据回答局部问题，符号评估器应用形式化规则检测非合规行为。我们在公司特定的 NDA 合规审查任务上实例化并评估了 PolicyGuard，需将合同条款与组织特定谈判政策比对。通过分离政策形式化、局部文档理解与符号合规评估，PolicyGuard 使文档审查更透明、可维护且可系统测试。
原文摘要 · Abstract (English)
Policy-grounded document review requires determining whether a target document complies with organization-specific policies, guidelines, or playbooks. While large language models can assist with policy interpretation and document analysis, end-to-end prompting leaves the applied policy logic implicit, making compliance decisions difficult to inspect, update, and test. We present PolicyGuard, a neuro-symbolic framework for policy-grounded document compliance review. PolicyGuard converts organizational policy guidance into an executable review engine consisting of typed relational logic rules and atom-level extraction questions. During review, LLMs answer these local questions using retrieved document evidence, and a symbolic evaluator applies the formal rules to detect non-compliance. We instantiate and evaluate PolicyGuard on company-specific NDA compliance review, where contract clauses must be checked against organization-specific negotiation policies. By separating policy formalization, local document interpretation, and symbolic compliance evaluation, PolicyGuard makes document review more explicit, maintainable, and systematically testable.
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。