@inproceedings{armannsson-etal-2025-icelandic,
title = "An {Icelandic} Linguistic Benchmark for Large Language Models",
author = "{\'A}rmannsson, Bjarki and
Ingimundarson, Finnur {\'A}g{\'u}st and
Sigur{\dh}sson, Einar Freyr",
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-1.5/",
pages = "37--47",
ISBN = "978-9908-53-109-0",
abstract = "This paper introduces a linguistic benchmark for Icelandic-language LLMs, the first of its kind manually constructed by native speakers. We report on the scores obtained by current state-of-the-art models, which indicate room for improvement, and discuss the theoretical problems involved in creating such a benchmark and scoring a model{'}s performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="armannsson-etal-2025-icelandic">
<titleInfo>
<title>An Icelandic Linguistic Benchmark for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bjarki</namePart>
<namePart type="family">Ármannsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Finnur</namePart>
<namePart type="given">Ágúst</namePart>
<namePart type="family">Ingimundarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Einar</namePart>
<namePart type="given">Freyr</namePart>
<namePart type="family">Sigur\dhsson</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 paper introduces a linguistic benchmark for Icelandic-language LLMs, the first of its kind manually constructed by native speakers. We report on the scores obtained by current state-of-the-art models, which indicate room for improvement, and discuss the theoretical problems involved in creating such a benchmark and scoring a model’s performance.</abstract>
<identifier type="citekey">armannsson-etal-2025-icelandic</identifier>
<location>
<url>https://aclanthology.org/2025.nodalida-1.5/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>37</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Icelandic Linguistic Benchmark for Large Language Models
%A Ármannsson, Bjarki
%A Ingimundarson, Finnur Ágúst
%A Sigur\dhsson, Einar Freyr
%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 armannsson-etal-2025-icelandic
%X This paper introduces a linguistic benchmark for Icelandic-language LLMs, the first of its kind manually constructed by native speakers. We report on the scores obtained by current state-of-the-art models, which indicate room for improvement, and discuss the theoretical problems involved in creating such a benchmark and scoring a model’s performance.
%U https://aclanthology.org/2025.nodalida-1.5/
%P 37-47
Markdown (Informal)
[An Icelandic Linguistic Benchmark for Large Language Models](https://aclanthology.org/2025.nodalida-1.5/) (Ármannsson et al., NoDaLiDa 2025)
ACL
- Bjarki Ármannsson, Finnur Ágúst Ingimundarson, and Einar Freyr Sigurðsson. 2025. An Icelandic Linguistic Benchmark for Large Language Models. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 37–47, Tallinn, Estonia. University of Tartu Library.