# Policy-Aware Generative AI for Safe, Auditable Data Access Governance

arXiv: https://arxiv.org/abs/2510.23474 · HTML: https://mlsanity.com/paper/2510.23474/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 34 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 1 of 1)

- [Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs](https://mlsanity.com/paper/2305.12138/) (2023)

## Built on by (most cited first, 3 of 3)

- [Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM](https://mlsanity.com/paper/2601.06627/) (2026)
- [Evaluating Semantic and Syntactic Understanding in Large Language Models for Payroll Systems](https://mlsanity.com/paper/2601.18012/) (2026)
- [Household Movement Detection in Mixed-Format Occupancy Data Using LLM-Based Entity Resolution](https://mlsanity.com/paper/2607.21614/) (2026)

## Abstract (arXiv)

Enterprises need access decisions that satisfy least privilege, comply with regulations, and remain auditable. We present a policy aware controller that uses a large language model (LLM) to interpret natural language requests against written policies and metadata, not raw data. The system, implemented with Google Gemini~2.0 Flash, executes a six-stage reasoning framework (context interpretation, user validation, data classification, business purpose test, compliance mapping, and risk synthesis) with early hard policy gates and deny by default. It returns APPROVE, DENY, CONDITIONAL together with cited controls and a machine readable rationale. We evaluate on fourteen canonical cases across seven scenario families using a privacy preserving benchmark. Results show Exact Decision Match improving from 10/14 to 13/14 (92.9%) after applying policy gates, DENY recall rising to 1.00, False Approval Rate on must-deny families dropping to 0, and Functional Appropriateness and Compliance Adherence at 14/14. Expert ratings of rationale quality are high, and median latency is under one minute. These findings indicate that policy constrained LLM reasoning, combined with explicit gates and audit trails, can translate human readable policies into safe, compliant, and traceable machine decisions.