<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trokhymovych-etal-2026-end">
    <titleInfo>
        <title>An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mykola</namePart>
        <namePart type="family">Trokhymovych</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yana</namePart>
        <namePart type="family">Oliinyk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nazarii</namePart>
        <namePart type="family">Nyzhnyk</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mariana</namePart>
            <namePart type="family">Romanyshyn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Lviv, Ukraine</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-359-3</identifier>
    </relatedItem>
    <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.</abstract>
    <identifier type="citekey">trokhymovych-etal-2026-end</identifier>
    <location>
        <url>https://aclanthology.org/2026.unlp-1.19/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>223</start>
            <end>229</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation
%A Trokhymovych, Mykola
%A Oliinyk, Yana
%A Nyzhnyk, Nazarii
%Y Romanyshyn, Mariana
%S Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026)
%D 2026
%8 May
%I Association for Computational Linguistics
%C Lviv, Ukraine
%@ 979-8-89176-359-3
%F trokhymovych-etal-2026-end
%X 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.
%U https://aclanthology.org/2026.unlp-1.19/
%P 223-229

Markdown (Informal)

[An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation](https://aclanthology.org/2026.unlp-1.19/) (Trokhymovych et al., UNLP 2026)

• An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation (Trokhymovych et al., UNLP 2026)

ACL

• Mykola Trokhymovych, Yana Oliinyk, and Nazarii Nyzhnyk. 2026. An End-to-End Ukrainian RAG for Local Deployment. Optimized Hybrid Search and Lightweight Generation. In Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026), pages 223–229, Lviv, Ukraine. Association for Computational Linguistics.