@inproceedings{scalvini-etal-2025-prompt,
title = "Prompt Engineering Enhances {Faroese} {MT,} but Only Humans Can Tell",
author = "Scalvini, Barbara and
Simonsen, Annika and
Debess, Iben Nyholm and
Einarsson, Hafsteinn",
editor = "Johansson, Richard and
Stymne, Sara",
booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2025.nodalida-1.63/",
pages = "622--633",
ISBN = "978-9908-53-109-0",
abstract = "This study evaluates GPT-4`s English-to-Faroese translation capabilities, comparing it with multilingual models on FLORES-200 and Sprotin datasets. We propose a prompt optimization strategy using Semantic Textual Similarity (STS) to improve translation quality. Human evaluation confirms the effectiveness of STS-based few-shot example selection, though automated metrics fail to capture these improvements. Our findings advance LLM applications for low-resource language translation while highlighting the need for better evaluation methods in this context."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scalvini-etal-2025-prompt">
<titleInfo>
<title>Prompt Engineering Enhances Faroese MT, but Only Humans Can Tell</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Simonsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hafsteinn</namePart>
<namePart type="family">Einarsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-109-0</identifier>
</relatedItem>
<abstract>This study evaluates GPT-4‘s English-to-Faroese translation capabilities, comparing it with multilingual models on FLORES-200 and Sprotin datasets. We propose a prompt optimization strategy using Semantic Textual Similarity (STS) to improve translation quality. Human evaluation confirms the effectiveness of STS-based few-shot example selection, though automated metrics fail to capture these improvements. Our findings advance LLM applications for low-resource language translation while highlighting the need for better evaluation methods in this context.</abstract>
<identifier type="citekey">scalvini-etal-2025-prompt</identifier>
<location>
<url>https://aclanthology.org/2025.nodalida-1.63/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>622</start>
<end>633</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompt Engineering Enhances Faroese MT, but Only Humans Can Tell
%A Scalvini, Barbara
%A Simonsen, Annika
%A Debess, Iben Nyholm
%A Einarsson, Hafsteinn
%Y Johansson, Richard
%Y Stymne, Sara
%S Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)
%D 2025
%8 March
%I University of Tartu Library
%C Tallinn, Estonia
%@ 978-9908-53-109-0
%F scalvini-etal-2025-prompt
%X This study evaluates GPT-4‘s English-to-Faroese translation capabilities, comparing it with multilingual models on FLORES-200 and Sprotin datasets. We propose a prompt optimization strategy using Semantic Textual Similarity (STS) to improve translation quality. Human evaluation confirms the effectiveness of STS-based few-shot example selection, though automated metrics fail to capture these improvements. Our findings advance LLM applications for low-resource language translation while highlighting the need for better evaluation methods in this context.
%U https://aclanthology.org/2025.nodalida-1.63/
%P 622-633
Markdown (Informal)
[Prompt Engineering Enhances Faroese MT, but Only Humans Can Tell](https://aclanthology.org/2025.nodalida-1.63/) (Scalvini et al., NoDaLiDa 2025)
ACL
- Barbara Scalvini, Annika Simonsen, Iben Nyholm Debess, and Hafsteinn Einarsson. 2025. Prompt Engineering Enhances Faroese MT, but Only Humans Can Tell. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 622–633, Tallinn, Estonia. University of Tartu Library.