# An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation

Source: [An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation](<https://www.sota2.com/research/paper/69eeed8c55a3c32af89f972e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-28T05:00:04.744Z

Authors: Mykola Trokhymovych, Yana Oliinyk, Nazarii Nyzhnyk

Published: 2026-04-23T21:59:59.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.22095>)

[PDF](<https://arxiv.org/pdf/2604.22095.pdf>)