@inproceedings{gaona-2026-univie,
title = "{U}ni{V}ie-{HAIT}rans at {WMT}26 Terminology Translation Task: Terminology-Guided Data Filtering and Few-Shot Fine-Tuning for Lightweight {LLM}s",
author = "Gaona, Miguel Angel Rios",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.122/",
pages = "1873--1880",
ISBN = "979-8-89176-474-3",
abstract = "Specialised domain translation using Large Language Models remains challenging due to terminology constraints, scarce in-domain parallel data, and the tendency of fine-tuning to degrade in-context learning performance. We present our submission for the English{--}Polish and Spanish{--}Basque translation in the Medical and Engineering {\&} Technology domains. Our method follows three stages: i) We extract in-domain terms from a terminology database and prompt a multilingual LLM to generate contextual sentences for each term. ii) We build an efficient search index over large-scale, unconstrained web-crawled and medical parallel corpora. Using the synthetic sentences as queries, we retrieve and filter the most semantically relevant pairs to build an in-domain fine-tuning dataset. iii) We structure our training instances with a mixture of 0-shot and semantically retrieved 5-shot prompts, and fine-tune lightweight multilingual LLMs (Gemma-3-4B, and Tiny-Aya-Global) via QLoRA. Fine-tuned Gemma-3 achieves the best results on held-out data across all metrics on English{--}Polish (Medical) and on Spanish{--}Basque (Engineering {\&} Technology), showing that few-shot fine-tuning enhances specialised domain translation quality and preserves in-context adaptation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaona-2026-univie">
<titleInfo>
<title>UniVie-HAITrans at WMT26 Terminology Translation Task: Terminology-Guided Data Filtering and Few-Shot Fine-Tuning for Lightweight LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Angel</namePart>
<namePart type="given">Rios</namePart>
<namePart type="family">Gaona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>Specialised domain translation using Large Language Models remains challenging due to terminology constraints, scarce in-domain parallel data, and the tendency of fine-tuning to degrade in-context learning performance. We present our submission for the English–Polish and Spanish–Basque translation in the Medical and Engineering & Technology domains. Our method follows three stages: i) We extract in-domain terms from a terminology database and prompt a multilingual LLM to generate contextual sentences for each term. ii) We build an efficient search index over large-scale, unconstrained web-crawled and medical parallel corpora. Using the synthetic sentences as queries, we retrieve and filter the most semantically relevant pairs to build an in-domain fine-tuning dataset. iii) We structure our training instances with a mixture of 0-shot and semantically retrieved 5-shot prompts, and fine-tune lightweight multilingual LLMs (Gemma-3-4B, and Tiny-Aya-Global) via QLoRA. Fine-tuned Gemma-3 achieves the best results on held-out data across all metrics on English–Polish (Medical) and on Spanish–Basque (Engineering & Technology), showing that few-shot fine-tuning enhances specialised domain translation quality and preserves in-context adaptation.</abstract>
<identifier type="citekey">gaona-2026-univie</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.122/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1873</start>
<end>1880</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniVie-HAITrans at WMT26 Terminology Translation Task: Terminology-Guided Data Filtering and Few-Shot Fine-Tuning for Lightweight LLMs
%A Gaona, Miguel Angel Rios
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F gaona-2026-univie
%X Specialised domain translation using Large Language Models remains challenging due to terminology constraints, scarce in-domain parallel data, and the tendency of fine-tuning to degrade in-context learning performance. We present our submission for the English–Polish and Spanish–Basque translation in the Medical and Engineering & Technology domains. Our method follows three stages: i) We extract in-domain terms from a terminology database and prompt a multilingual LLM to generate contextual sentences for each term. ii) We build an efficient search index over large-scale, unconstrained web-crawled and medical parallel corpora. Using the synthetic sentences as queries, we retrieve and filter the most semantically relevant pairs to build an in-domain fine-tuning dataset. iii) We structure our training instances with a mixture of 0-shot and semantically retrieved 5-shot prompts, and fine-tune lightweight multilingual LLMs (Gemma-3-4B, and Tiny-Aya-Global) via QLoRA. Fine-tuned Gemma-3 achieves the best results on held-out data across all metrics on English–Polish (Medical) and on Spanish–Basque (Engineering & Technology), showing that few-shot fine-tuning enhances specialised domain translation quality and preserves in-context adaptation.
%U https://aclanthology.org/2026.wmt-main.122/
%P 1873-1880
Markdown (Informal)
[UniVie-HAITrans at WMT26 Terminology Translation Task: Terminology-Guided Data Filtering and Few-Shot Fine-Tuning for Lightweight LLMs](https://aclanthology.org/2026.wmt-main.122/) (Gaona, WMT 2026)
ACL