PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines
2026-06-30 • Artificial Intelligence
Artificial IntelligenceMachine LearningLogic in Computer ScienceSymbolic Computation
AI summaryⓘ
The authors created PolicyGuard, a system that helps check if documents follow specific company rules. Instead of letting a language model decide all at once, PolicyGuard breaks down the policy into clear rules and specific questions. The language model finds answers in the document, and a symbolic logic engine uses those answers to see if the document follows the rules. This approach makes it easier to understand, update, and test how document compliance is checked. They tested this on reviewing nondisclosure agreements to ensure they match company policies.
policy compliancelarge language modelsneuro-symbolic systemsrelational logic rulesdocument reviewnon-disclosure agreementpolicy formalizationsymbolic evaluationcontract analysisinformation extraction
Authors
Sameer Malik, Ayush Singh, Amar Prakash Azad
Abstract
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.