@inproceedings{hertzberg-lokrantz-2024-medqa-swe,
title = "{M}ed{QA}-{SWE} - a Clinical Question {\&} Answer Dataset for {S}wedish",
author = "Hertzberg, Niclas and
Lokrantz, Anna",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.975",
pages = "11178--11186",
abstract = "Considering the rapid improvement of large generative language models, it is important to measure their ability to encode clinical domain knowledge in order to help determine their potential utility in a clinical setting. To this end we present MedQA-SWE {--} a novel multiple choice, clinical question {\&} answering (Q{\&}A) dataset in Swedish consisting of 3,180 questions. The dataset was created from a series of exams aimed at evaluating doctors{'} clinical understanding and decision making and is the first open-source clinical Q{\&}A dataset in Swedish. The exams {--} originally in PDF format {--} were parsed and each question manually checked and curated in order to limit errors in the dataset. We provide dataset statistics along with benchmark accuracy scores of seven large generative language models on a representative sample of questions in a zero-shot setting, with some models showing impressive performance given the difficulty of the exam the dataset is based on.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hertzberg-lokrantz-2024-medqa-swe">
<titleInfo>
<title>MedQA-SWE - a Clinical Question & Answer Dataset for Swedish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niclas</namePart>
<namePart type="family">Hertzberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Lokrantz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Considering the rapid improvement of large generative language models, it is important to measure their ability to encode clinical domain knowledge in order to help determine their potential utility in a clinical setting. To this end we present MedQA-SWE – a novel multiple choice, clinical question & answering (Q&A) dataset in Swedish consisting of 3,180 questions. The dataset was created from a series of exams aimed at evaluating doctors’ clinical understanding and decision making and is the first open-source clinical Q&A dataset in Swedish. The exams – originally in PDF format – were parsed and each question manually checked and curated in order to limit errors in the dataset. We provide dataset statistics along with benchmark accuracy scores of seven large generative language models on a representative sample of questions in a zero-shot setting, with some models showing impressive performance given the difficulty of the exam the dataset is based on.</abstract>
<identifier type="citekey">hertzberg-lokrantz-2024-medqa-swe</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.975</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11178</start>
<end>11186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedQA-SWE - a Clinical Question & Answer Dataset for Swedish
%A Hertzberg, Niclas
%A Lokrantz, Anna
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F hertzberg-lokrantz-2024-medqa-swe
%X Considering the rapid improvement of large generative language models, it is important to measure their ability to encode clinical domain knowledge in order to help determine their potential utility in a clinical setting. To this end we present MedQA-SWE – a novel multiple choice, clinical question & answering (Q&A) dataset in Swedish consisting of 3,180 questions. The dataset was created from a series of exams aimed at evaluating doctors’ clinical understanding and decision making and is the first open-source clinical Q&A dataset in Swedish. The exams – originally in PDF format – were parsed and each question manually checked and curated in order to limit errors in the dataset. We provide dataset statistics along with benchmark accuracy scores of seven large generative language models on a representative sample of questions in a zero-shot setting, with some models showing impressive performance given the difficulty of the exam the dataset is based on.
%U https://aclanthology.org/2024.lrec-main.975
%P 11178-11186
Markdown (Informal)
[MedQA-SWE - a Clinical Question & Answer Dataset for Swedish](https://aclanthology.org/2024.lrec-main.975) (Hertzberg & Lokrantz, LREC-COLING 2024)
ACL