@inproceedings{mikhailov-etal-2025-collection,
title = "A Collection of Question Answering Datasets for {Norwegian}",
author = "Mikhailov, Vladislav and
M{\ae}hlum, Petter and
Lang{\o}, Victoria Ovedie Chruickshank and
Velldal, Erik and
{\O}vrelid, Lilja",
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-1.43/",
pages = "397--407",
ISBN = "978-9908-53-109-0",
abstract = "This paper introduces a new suite of question answering datasets for Norwegian; NorOpenBookQA, NorCommonSenseQA, NorTruthfulQA, and NRK-Quiz-QA. The data covers a wide range of skills and knowledge domains, including world knowledge, commonsense reasoning, truthfulness, and knowledge about Norway. Covering both of the written standards of Norwegian {--} Bokm{\r{a}}l and Nynorsk {--} our datasets comprise over 10k question-answer pairs, created by native speakers. We detail our dataset creation approach and present the results of evaluating 11 language models (LMs) in zero- and few-shot regimes. Most LMs perform better in Bokm{\r{a}}l than Nynorsk, struggle most with commonsense reasoning, and are often untruthful in generating answers to questions. All our datasets and annotation materials are publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mikhailov-etal-2025-collection">
<titleInfo>
<title>A Collection of Question Answering Datasets for Norwegian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petter</namePart>
<namePart type="family">Mæhlum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="given">Ovedie</namePart>
<namePart type="given">Chruickshank</namePart>
<namePart type="family">Langø</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Velldal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</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 new suite of question answering datasets for Norwegian; NorOpenBookQA, NorCommonSenseQA, NorTruthfulQA, and NRK-Quiz-QA. The data covers a wide range of skills and knowledge domains, including world knowledge, commonsense reasoning, truthfulness, and knowledge about Norway. Covering both of the written standards of Norwegian – Bokmål and Nynorsk – our datasets comprise over 10k question-answer pairs, created by native speakers. We detail our dataset creation approach and present the results of evaluating 11 language models (LMs) in zero- and few-shot regimes. Most LMs perform better in Bokmål than Nynorsk, struggle most with commonsense reasoning, and are often untruthful in generating answers to questions. All our datasets and annotation materials are publicly available.</abstract>
<identifier type="citekey">mikhailov-etal-2025-collection</identifier>
<location>
<url>https://aclanthology.org/2025.nodalida-1.43/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>397</start>
<end>407</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Collection of Question Answering Datasets for Norwegian
%A Mikhailov, Vladislav
%A Mæhlum, Petter
%A Langø, Victoria Ovedie Chruickshank
%A Velldal, Erik
%A Øvrelid, Lilja
%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 mikhailov-etal-2025-collection
%X This paper introduces a new suite of question answering datasets for Norwegian; NorOpenBookQA, NorCommonSenseQA, NorTruthfulQA, and NRK-Quiz-QA. The data covers a wide range of skills and knowledge domains, including world knowledge, commonsense reasoning, truthfulness, and knowledge about Norway. Covering both of the written standards of Norwegian – Bokmål and Nynorsk – our datasets comprise over 10k question-answer pairs, created by native speakers. We detail our dataset creation approach and present the results of evaluating 11 language models (LMs) in zero- and few-shot regimes. Most LMs perform better in Bokmål than Nynorsk, struggle most with commonsense reasoning, and are often untruthful in generating answers to questions. All our datasets and annotation materials are publicly available.
%U https://aclanthology.org/2025.nodalida-1.43/
%P 397-407
Markdown (Informal)
[A Collection of Question Answering Datasets for Norwegian](https://aclanthology.org/2025.nodalida-1.43/) (Mikhailov et al., NoDaLiDa 2025)
ACL
- Vladislav Mikhailov, Petter Mæhlum, Victoria Ovedie Chruickshank Langø, Erik Velldal, and Lilja Øvrelid. 2025. A Collection of Question Answering Datasets for Norwegian. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 397–407, Tallinn, Estonia. University of Tartu Library.