@inproceedings{frontull-strohle-2026-every,
title = "Every Word Presented in Context: Syntactic Coverage as Objective for Low-Resource Machine Translation with Large Language Models",
author = {Frontull, Samuel and
Str{\"o}hle, Thomas},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.694/",
doi = "10.63317/5jpokiam9tjt",
pages = "8824--8837",
abstract = {Large Language Models (LLMs) have demonstrated strong capabilities in multilingual machine translation. However, they underperform for low-resource languages, indicating the need for more explicit instructional guidance. In this work, we introduce Fragment-Shot Prompting, a novel few-shot prompting method that aims to retrieve examples for every word occurring in the sentence to be translated, illustrating their use and meaning in context. We evaluate our method on translation between Italian, Ladin (Val Badia) and Ladin (Gherd{\"e}ina) and compare its performance with zero-shot prompting, random few-shot prompting, as well as established lexical and semantic retrieval strategies. We conduct these experiments using state-of-the-art LLMs, including GPT-3.5, GPT-4o, o1-mini, LlaMA-3.3, and DeepSeek-R1. Our results demonstrate that LLMs can extract substantial value from limited data when translating from a low- to the high-resource language. However, this does not apply to translations into the low-resource languages, where the prompting method plays a much more important role. In particular, our method consistently delivers the best results and enables significant gains. Even though translation performance into Ladin remains limited with the available resources, our results highlight the importance of syntactic coverage for improving translation accuracy and ariant-specific adaptation in low-resource scenarios.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="frontull-strohle-2026-every">
<titleInfo>
<title>Every Word Presented in Context: Syntactic Coverage as Objective for Low-Resource Machine Translation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Frontull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Ströhle</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated strong capabilities in multilingual machine translation. However, they underperform for low-resource languages, indicating the need for more explicit instructional guidance. In this work, we introduce Fragment-Shot Prompting, a novel few-shot prompting method that aims to retrieve examples for every word occurring in the sentence to be translated, illustrating their use and meaning in context. We evaluate our method on translation between Italian, Ladin (Val Badia) and Ladin (Gherdëina) and compare its performance with zero-shot prompting, random few-shot prompting, as well as established lexical and semantic retrieval strategies. We conduct these experiments using state-of-the-art LLMs, including GPT-3.5, GPT-4o, o1-mini, LlaMA-3.3, and DeepSeek-R1. Our results demonstrate that LLMs can extract substantial value from limited data when translating from a low- to the high-resource language. However, this does not apply to translations into the low-resource languages, where the prompting method plays a much more important role. In particular, our method consistently delivers the best results and enables significant gains. Even though translation performance into Ladin remains limited with the available resources, our results highlight the importance of syntactic coverage for improving translation accuracy and ariant-specific adaptation in low-resource scenarios.</abstract>
<identifier type="citekey">frontull-strohle-2026-every</identifier>
<identifier type="doi">10.63317/5jpokiam9tjt</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.694/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8824</start>
<end>8837</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Every Word Presented in Context: Syntactic Coverage as Objective for Low-Resource Machine Translation with Large Language Models
%A Frontull, Samuel
%A Ströhle, Thomas
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F frontull-strohle-2026-every
%X Large Language Models (LLMs) have demonstrated strong capabilities in multilingual machine translation. However, they underperform for low-resource languages, indicating the need for more explicit instructional guidance. In this work, we introduce Fragment-Shot Prompting, a novel few-shot prompting method that aims to retrieve examples for every word occurring in the sentence to be translated, illustrating their use and meaning in context. We evaluate our method on translation between Italian, Ladin (Val Badia) and Ladin (Gherdëina) and compare its performance with zero-shot prompting, random few-shot prompting, as well as established lexical and semantic retrieval strategies. We conduct these experiments using state-of-the-art LLMs, including GPT-3.5, GPT-4o, o1-mini, LlaMA-3.3, and DeepSeek-R1. Our results demonstrate that LLMs can extract substantial value from limited data when translating from a low- to the high-resource language. However, this does not apply to translations into the low-resource languages, where the prompting method plays a much more important role. In particular, our method consistently delivers the best results and enables significant gains. Even though translation performance into Ladin remains limited with the available resources, our results highlight the importance of syntactic coverage for improving translation accuracy and ariant-specific adaptation in low-resource scenarios.
%R 10.63317/5jpokiam9tjt
%U https://aclanthology.org/2026.lrec-1.694/
%U https://doi.org/10.63317/5jpokiam9tjt
%P 8824-8837
Markdown (Informal)
[Every Word Presented in Context: Syntactic Coverage as Objective for Low-Resource Machine Translation with Large Language Models](https://aclanthology.org/2026.lrec-1.694/) (Frontull & Ströhle, LREC 2026)
ACL