Saved in:
Bibliographic Details
Main Authors: Trokhymovych, Mykola, Oliinyk, Yana, Nyzhnyk, Nazarii
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22095
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915953066901504
author Trokhymovych, Mykola
Oliinyk, Yana
Nyzhnyk, Nazarii
author_facet Trokhymovych, Mykola
Oliinyk, Yana
Nyzhnyk, Nazarii
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22095
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
Trokhymovych, Mykola
Oliinyk, Yana
Nyzhnyk, Nazarii
Computation and Language
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.
title An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
topic Computation and Language
url https://arxiv.org/abs/2604.22095