RAGAL: Fully Local Retrieval-Augmented Assistant for Government Technical Support Achieves 81% Accuracy on Sensitive Data
Researchers developed RAGAL, a retrieval-augmented assistant deployed for the Romanian Agency for Financing Rural Investments (AFIR) under strict constraints: zero data egress, a read-only mandate, and operation on a single 8 GB laptop. By combining hybrid dense-sparse retrieval with intent routing, internal evaluation accuracy improved from 62% to 81%. Fine-tuning the bge-m3 embedder on real support ticket data further increased recall@10 from 0.663 to 0.850 after 72 minutes of training.
Why it matters: This work demonstrates a practical and reproducible approach for building effective AI assistants in sensitive government environments where cloud-based solutions are not permitted.
Full story at: arXiv Information Retrieval ↗