{"ID":5443889,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-03T17:12:03.69683831Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.32004","arxiv_id":"2606.32004","title":"PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines","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.","short_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...","url_abs":"https://arxiv.org/abs/2606.32004","url_pdf":"https://arxiv.org/pdf/2606.32004v1","authors":"[\"Sameer Malik\",\"Ayush Singh\",\"Amar Prakash Azad\"]","published":"2026-06-30T17:37:57Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\",\"cs.LO\",\"cs.SC\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}