@inproceedings{kim-etal-2024-medexqa,
title = "{M}ed{E}x{QA}: Medical Question Answering Benchmark with Multiple Explanations",
author = "Kim, Yunsoo and
Wu, Jinge and
Abdulle, Yusuf and
Wu, Honghan",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.14",
pages = "167--181",
abstract = "This paper introduces MedExQA, a novel benchmark in medical question-answering, to evaluate large language models{'} (LLMs) understanding of medical knowledge through explanations. By constructing datasets across five distinct medical specialties that are underrepresented in current datasets and further incorporating multiple explanations for each question-answer pair, we address a major gap in current medical QA benchmarks which is the absence of comprehensive assessments of LLMs{'} ability to generate nuanced medical explanations. Our work highlights the importance of explainability in medical LLMs, proposes an effective methodology for evaluating models beyond classification accuracy, and sheds light on one specific domain, speech language pathology, where current LLMs including GPT4 lack good understanding. Our results show generation evaluation with multiple explanations aligns better with human assessment, highlighting an opportunity for a more robust automated comprehension assessment for LLMs. To diversify open-source medical LLMs (currently mostly based on Llama2), this work also proposes a new medical model, MedPhi-2, based on Phi-2 (2.7B). The model outperformed medical LLMs based on Llama2-70B in generating explanations, showing its effectiveness in the resource-constrained medical domain. We will share our benchmark datasets and the trained model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-medexqa">
<titleInfo>
<title>MedExQA: Medical Question Answering Benchmark with Multiple Explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunsoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinge</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuf</namePart>
<namePart type="family">Abdulle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Honghan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces MedExQA, a novel benchmark in medical question-answering, to evaluate large language models’ (LLMs) understanding of medical knowledge through explanations. By constructing datasets across five distinct medical specialties that are underrepresented in current datasets and further incorporating multiple explanations for each question-answer pair, we address a major gap in current medical QA benchmarks which is the absence of comprehensive assessments of LLMs’ ability to generate nuanced medical explanations. Our work highlights the importance of explainability in medical LLMs, proposes an effective methodology for evaluating models beyond classification accuracy, and sheds light on one specific domain, speech language pathology, where current LLMs including GPT4 lack good understanding. Our results show generation evaluation with multiple explanations aligns better with human assessment, highlighting an opportunity for a more robust automated comprehension assessment for LLMs. To diversify open-source medical LLMs (currently mostly based on Llama2), this work also proposes a new medical model, MedPhi-2, based on Phi-2 (2.7B). The model outperformed medical LLMs based on Llama2-70B in generating explanations, showing its effectiveness in the resource-constrained medical domain. We will share our benchmark datasets and the trained model.</abstract>
<identifier type="citekey">kim-etal-2024-medexqa</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.14</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>167</start>
<end>181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedExQA: Medical Question Answering Benchmark with Multiple Explanations
%A Kim, Yunsoo
%A Wu, Jinge
%A Abdulle, Yusuf
%A Wu, Honghan
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F kim-etal-2024-medexqa
%X This paper introduces MedExQA, a novel benchmark in medical question-answering, to evaluate large language models’ (LLMs) understanding of medical knowledge through explanations. By constructing datasets across five distinct medical specialties that are underrepresented in current datasets and further incorporating multiple explanations for each question-answer pair, we address a major gap in current medical QA benchmarks which is the absence of comprehensive assessments of LLMs’ ability to generate nuanced medical explanations. Our work highlights the importance of explainability in medical LLMs, proposes an effective methodology for evaluating models beyond classification accuracy, and sheds light on one specific domain, speech language pathology, where current LLMs including GPT4 lack good understanding. Our results show generation evaluation with multiple explanations aligns better with human assessment, highlighting an opportunity for a more robust automated comprehension assessment for LLMs. To diversify open-source medical LLMs (currently mostly based on Llama2), this work also proposes a new medical model, MedPhi-2, based on Phi-2 (2.7B). The model outperformed medical LLMs based on Llama2-70B in generating explanations, showing its effectiveness in the resource-constrained medical domain. We will share our benchmark datasets and the trained model.
%U https://aclanthology.org/2024.bionlp-1.14
%P 167-181
Markdown (Informal)
[MedExQA: Medical Question Answering Benchmark with Multiple Explanations](https://aclanthology.org/2024.bionlp-1.14) (Kim et al., BioNLP-WS 2024)
ACL