<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shpigunov-2026-improving">
    <titleInfo>
        <title>Improving Domain-Specific Translation from English into Ukrainian with Retrieval-Augmented Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Anton</namePart>
        <namePart type="family">Shpigunov</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>Large language models have demonstrated competence as language translators, including for lower-resourced languages like Ukrainian. However, in specialized or novel domains, translation quality can suffer without adequate lexical and stylistic reference material. We present a retrieval-augmented approach to English-Ukrainian machine translation in a narrow domain: a private legal/military bilingual corpus. In this approach, semantically similar translation units retrieved via vector embeddings are provided as in-context examples to the LLM. We evaluate three open-weight Gemma 3 models, 4B, 12B, and 27B, against Gemini 3 Flash as a baseline across five augmentation conditions, with k values of 0, 3, 5, 10, and 25, on a 2,581-pair index and a 258-pair test set. We find that context augmentation yields statistically significant improvements in both ChrF++ and COMET for all models, with the smallest model’s COMET score improving by 0.076 at k = 3. However, smaller models exhibit context saturation: the 4B model’s performance peaks at k = 10 and degrades with additional context, losing 9.72 ChrF++ points and 0.007 COMET between k = 10 and k = 25, while larger models continue to benefit.</abstract>
    <identifier type="citekey">shpigunov-2026-improving</identifier>
    <location>
        <url>https://aclanthology.org/2026.unlp-1.1/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>1</start>
            <end>11</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Domain-Specific Translation from English into Ukrainian with Retrieval-Augmented Generation
%A Shpigunov, Anton
%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 shpigunov-2026-improving
%X Large language models have demonstrated competence as language translators, including for lower-resourced languages like Ukrainian. However, in specialized or novel domains, translation quality can suffer without adequate lexical and stylistic reference material. We present a retrieval-augmented approach to English-Ukrainian machine translation in a narrow domain: a private legal/military bilingual corpus. In this approach, semantically similar translation units retrieved via vector embeddings are provided as in-context examples to the LLM. We evaluate three open-weight Gemma 3 models, 4B, 12B, and 27B, against Gemini 3 Flash as a baseline across five augmentation conditions, with k values of 0, 3, 5, 10, and 25, on a 2,581-pair index and a 258-pair test set. We find that context augmentation yields statistically significant improvements in both ChrF++ and COMET for all models, with the smallest model’s COMET score improving by 0.076 at k = 3. However, smaller models exhibit context saturation: the 4B model’s performance peaks at k = 10 and degrades with additional context, losing 9.72 ChrF++ points and 0.007 COMET between k = 10 and k = 25, while larger models continue to benefit.
%U https://aclanthology.org/2026.unlp-1.1/
%P 1-11

Markdown (Informal)

[Improving Domain-Specific Translation from English into Ukrainian with Retrieval-Augmented Generation](https://aclanthology.org/2026.unlp-1.1/) (Shpigunov, UNLP 2026)

• Improving Domain-Specific Translation from English into Ukrainian with Retrieval-Augmented Generation (Shpigunov, UNLP 2026)

ACL

• Anton Shpigunov. 2026. Improving Domain-Specific Translation from English into Ukrainian with Retrieval-Augmented Generation. In Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026), pages 1–11, Lviv, Ukraine. Association for Computational Linguistics.