Hendrika Maclean

Hendrika Maclean, Mert Can Cakmak, Muzakkiruddin Ahmed Mohammed et al.

Large language models are now used daily for writing, search, and analysis, and their natural language understanding continues to improve. However, they remain unreliable on exact numerical calculation and on producing outputs that are straightforward to audit. We study synthetic payroll system as a focused, high-stakes example and evaluate whether models can understand a payroll schema, apply rules in the right order, and deliver cent-accurate results. Our experiments span a tiered dataset from basic to complex cases, a spectrum of prompts from minimal baselines to schema-guided and reasoning variants, and multiple model families including GPT, Claude, Perplexity, Grok and Gemini. Results indicate clear regimes where careful prompting is sufficient and regimes where explicit computation is required. The work offers a compact, reproducible framework and practical guidance for deploying LLMs in settings that demand both accuracy and assurance.

Shames Al Mandalawi, Muzakkiruddin Ahmed Mohammed, Hendrika Maclean et al.

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.