@inproceedings{wang-etal-2025-mesaqa,
title = "{MESAQA}: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering",
author = "Wang, Jui-I and
Huang, Hen-Hsen and
Chen, Hsin-Hsi",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.724/",
pages = "10891--10901",
abstract = "We introduce MESAQA, a novel dataset focusing on multi-span contextual understanding question answering (QA).Unlike traditional single-span QA systems, questions in our dataset consider information from multiple spans within the context document. MESAQA supports evidence-grounded QA, demanding the model`s capability of answer generation and multi-evidence identification. Our automated dataset creation method leverages the MASH-QA dataset and large language models (LLMs) to ensure that each Q/A pair requires considering all selected spans. Experimental results show that current models struggle with multi-span contextual QA, underscoring the need for new approaches. Our dataset sets a benchmark for this emerging QA paradigm, promoting research in complex information retrieval and synthesis."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-mesaqa">
<titleInfo>
<title>MESAQA: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jui-I</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hen-Hsen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce MESAQA, a novel dataset focusing on multi-span contextual understanding question answering (QA).Unlike traditional single-span QA systems, questions in our dataset consider information from multiple spans within the context document. MESAQA supports evidence-grounded QA, demanding the model‘s capability of answer generation and multi-evidence identification. Our automated dataset creation method leverages the MASH-QA dataset and large language models (LLMs) to ensure that each Q/A pair requires considering all selected spans. Experimental results show that current models struggle with multi-span contextual QA, underscoring the need for new approaches. Our dataset sets a benchmark for this emerging QA paradigm, promoting research in complex information retrieval and synthesis.</abstract>
<identifier type="citekey">wang-etal-2025-mesaqa</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.724/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>10891</start>
<end>10901</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MESAQA: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering
%A Wang, Jui-I
%A Huang, Hen-Hsen
%A Chen, Hsin-Hsi
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F wang-etal-2025-mesaqa
%X We introduce MESAQA, a novel dataset focusing on multi-span contextual understanding question answering (QA).Unlike traditional single-span QA systems, questions in our dataset consider information from multiple spans within the context document. MESAQA supports evidence-grounded QA, demanding the model‘s capability of answer generation and multi-evidence identification. Our automated dataset creation method leverages the MASH-QA dataset and large language models (LLMs) to ensure that each Q/A pair requires considering all selected spans. Experimental results show that current models struggle with multi-span contextual QA, underscoring the need for new approaches. Our dataset sets a benchmark for this emerging QA paradigm, promoting research in complex information retrieval and synthesis.
%U https://aclanthology.org/2025.coling-main.724/
%P 10891-10901
Markdown (Informal)
[MESAQA: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering](https://aclanthology.org/2025.coling-main.724/) (Wang et al., COLING 2025)
ACL