@inproceedings{moerman-tezcan-2026-getting,
title = "Getting More from Small {LLM}s and Limited Data: Fuzzy-Match Retrieval and Candidate Scoring for Multitask Sorbian {NLP}",
author = "Moerman, Thomas and
Tezcan, Arda",
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.211/",
pages = "2668--2681",
ISBN = "979-8-89176-474-3",
abstract = "We describe LT3{'}s submission to the WMT26 shared task on Multitask LLMs with Limited Resources for Upper Sorbian (hsb) and Lower Sorbian (dsb): one QLoRA-fine-tuned Qwen3.5-2B model serves machine translation, multiple-choice question answering, spell checking, grammar checking, and maths reasoning. Our approach centres on three components. First, retrieval augmentation: fuzzy-match (FM) exemplars, retrieved by character- and embedding-based similarity from authentic and back-translated sentence pools, are included in prompts at training and inference times. Second, synthetic task data: training data for spell- and grammar-checking is generated from dictionaries and monolingual text. Third, a scoring-based inference system: the model generates free text only for the open-ended tasks{--}translation and maths reasoning{--}while, for the other three tasks, it scores candidates from constrained spaces by ranking multiple-choice options in place and selecting spelling and grammar corrections from dictionary-derived candidates. Our primary system was the joint winner of the Sorbian track, ranking first or second across all five tasks and outperforming the next-best system by 7.7 accuracy points on question answering and 1.4 points on mathematical reasoning. These results show that, for low-resource languages, FM augmentation combined with back-translation can improve MT performance for a relatively small LLM, while inference-level strategies can further improve its performance on other tasks without compromising MT performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moerman-tezcan-2026-getting">
<titleInfo>
<title>Getting More from Small LLMs and Limited Data: Fuzzy-Match Retrieval and Candidate Scoring for Multitask Sorbian NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Moerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Tezcan</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>We describe LT3’s submission to the WMT26 shared task on Multitask LLMs with Limited Resources for Upper Sorbian (hsb) and Lower Sorbian (dsb): one QLoRA-fine-tuned Qwen3.5-2B model serves machine translation, multiple-choice question answering, spell checking, grammar checking, and maths reasoning. Our approach centres on three components. First, retrieval augmentation: fuzzy-match (FM) exemplars, retrieved by character- and embedding-based similarity from authentic and back-translated sentence pools, are included in prompts at training and inference times. Second, synthetic task data: training data for spell- and grammar-checking is generated from dictionaries and monolingual text. Third, a scoring-based inference system: the model generates free text only for the open-ended tasks–translation and maths reasoning–while, for the other three tasks, it scores candidates from constrained spaces by ranking multiple-choice options in place and selecting spelling and grammar corrections from dictionary-derived candidates. Our primary system was the joint winner of the Sorbian track, ranking first or second across all five tasks and outperforming the next-best system by 7.7 accuracy points on question answering and 1.4 points on mathematical reasoning. These results show that, for low-resource languages, FM augmentation combined with back-translation can improve MT performance for a relatively small LLM, while inference-level strategies can further improve its performance on other tasks without compromising MT performance.</abstract>
<identifier type="citekey">moerman-tezcan-2026-getting</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.211/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2668</start>
<end>2681</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Getting More from Small LLMs and Limited Data: Fuzzy-Match Retrieval and Candidate Scoring for Multitask Sorbian NLP
%A Moerman, Thomas
%A Tezcan, Arda
%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 moerman-tezcan-2026-getting
%X We describe LT3’s submission to the WMT26 shared task on Multitask LLMs with Limited Resources for Upper Sorbian (hsb) and Lower Sorbian (dsb): one QLoRA-fine-tuned Qwen3.5-2B model serves machine translation, multiple-choice question answering, spell checking, grammar checking, and maths reasoning. Our approach centres on three components. First, retrieval augmentation: fuzzy-match (FM) exemplars, retrieved by character- and embedding-based similarity from authentic and back-translated sentence pools, are included in prompts at training and inference times. Second, synthetic task data: training data for spell- and grammar-checking is generated from dictionaries and monolingual text. Third, a scoring-based inference system: the model generates free text only for the open-ended tasks–translation and maths reasoning–while, for the other three tasks, it scores candidates from constrained spaces by ranking multiple-choice options in place and selecting spelling and grammar corrections from dictionary-derived candidates. Our primary system was the joint winner of the Sorbian track, ranking first or second across all five tasks and outperforming the next-best system by 7.7 accuracy points on question answering and 1.4 points on mathematical reasoning. These results show that, for low-resource languages, FM augmentation combined with back-translation can improve MT performance for a relatively small LLM, while inference-level strategies can further improve its performance on other tasks without compromising MT performance.
%U https://aclanthology.org/2026.wmt-main.211/
%P 2668-2681
Markdown (Informal)
[Getting More from Small LLMs and Limited Data: Fuzzy-Match Retrieval and Candidate Scoring for Multitask Sorbian NLP](https://aclanthology.org/2026.wmt-main.211/) (Moerman & Tezcan, WMT 2026)
ACL