Faheem Ullah Khan

Benchmarking Classical and Transformer-Based Models for Document Sensitivity Classification

This paper introduces Strategic 16K, a carefully constructed, leakage-controlled corpus of 16,000 diplomatic cables sourced from the WikiLeaks Public Library of US Diplomacy (PlusD), and presents a systematic benchmark evaluating six model architectures spanning classical machine learning and transformer-based approaches, creating the first fully reproducible sensitivity classification benchmark constructed under explicit leakage-controlled conditions from WikiLeaks PlusD.