This paper presents a highly efficient Retrieval-Augmented Generation (RAG) system built specifically for Ukrainian document question answering, which achieved 2nd place in the UNLP 2026 Shared Task. Our solution features a custom two-stage search pipeline that retrieves relevant document pages, paired with a specialized Ukrainian language model fine-tuned on synthetic data to generate accurate, grounded answers. Finally, we compress the model for lightweight deployment. Evaluated under strict computational limits, our architecture demonstrates that high-quality, verifiable AI question answering can be achieved locally on resource-constrained hardware without sacrificing accuracy.
@article{arxiv.2604.22095,
title = {An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation},
author = {Mykola Trokhymovych and Yana Oliinyk and Nazarii Nyzhnyk},
journal= {arXiv preprint arXiv:2604.22095},
year = {2026}
}