@inproceedings{kim-etal-2023-qa,
title = "({QA})$^2$: Question Answering with Questionable Assumptions",
author = "Kim, Najoung and
Htut, Phu Mon and
Bowman, Samuel R. and
Petty, Jackson",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.472",
doi = "10.18653/v1/2023.acl-long.472",
pages = "8466--8487",
abstract = "Naturally occurring information-seeking questions often contain questionable assumptions{---}assumptions that are false or unverifiable. Questions containing questionable assumptions are challenging because they require a distinct answer strategy that deviates from typical answers for information-seeking questions. For instance, the question {``}When did Marie Curie discover Uranium?{''} cannot be answered as a typical {``}when{''} question without addressing the false assumption {``}Marie Curie discovered Uranium{''}. In this work, we propose (QA)2 (Question Answering with Questionable Assumptions), an open-domain evaluation dataset consisting of naturally occurring search engine queries that may or may not contain questionable assumptions. To be successful on (QA)2, systems must be able to detect questionable assumptions and also be able to produce adequate responses for both typical information-seeking questions and ones with questionable assumptions. Through human rater acceptability on end-to-end QA with (QA)2, we find that current models do struggle with handling questionable assumptions, leaving substantial headroom for progress.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2023-qa">
<titleInfo>
<title>(QA)²: Question Answering with Questionable Assumptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Najoung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phu</namePart>
<namePart type="given">Mon</namePart>
<namePart type="family">Htut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Bowman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="family">Petty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Naturally occurring information-seeking questions often contain questionable assumptions—assumptions that are false or unverifiable. Questions containing questionable assumptions are challenging because they require a distinct answer strategy that deviates from typical answers for information-seeking questions. For instance, the question “When did Marie Curie discover Uranium?” cannot be answered as a typical “when” question without addressing the false assumption “Marie Curie discovered Uranium”. In this work, we propose (QA)2 (Question Answering with Questionable Assumptions), an open-domain evaluation dataset consisting of naturally occurring search engine queries that may or may not contain questionable assumptions. To be successful on (QA)2, systems must be able to detect questionable assumptions and also be able to produce adequate responses for both typical information-seeking questions and ones with questionable assumptions. Through human rater acceptability on end-to-end QA with (QA)2, we find that current models do struggle with handling questionable assumptions, leaving substantial headroom for progress.</abstract>
<identifier type="citekey">kim-etal-2023-qa</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.472</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.472</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>8466</start>
<end>8487</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T (QA)²: Question Answering with Questionable Assumptions
%A Kim, Najoung
%A Htut, Phu Mon
%A Bowman, Samuel R.
%A Petty, Jackson
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kim-etal-2023-qa
%X Naturally occurring information-seeking questions often contain questionable assumptions—assumptions that are false or unverifiable. Questions containing questionable assumptions are challenging because they require a distinct answer strategy that deviates from typical answers for information-seeking questions. For instance, the question “When did Marie Curie discover Uranium?” cannot be answered as a typical “when” question without addressing the false assumption “Marie Curie discovered Uranium”. In this work, we propose (QA)2 (Question Answering with Questionable Assumptions), an open-domain evaluation dataset consisting of naturally occurring search engine queries that may or may not contain questionable assumptions. To be successful on (QA)2, systems must be able to detect questionable assumptions and also be able to produce adequate responses for both typical information-seeking questions and ones with questionable assumptions. Through human rater acceptability on end-to-end QA with (QA)2, we find that current models do struggle with handling questionable assumptions, leaving substantial headroom for progress.
%R 10.18653/v1/2023.acl-long.472
%U https://aclanthology.org/2023.acl-long.472
%U https://doi.org/10.18653/v1/2023.acl-long.472
%P 8466-8487
Markdown (Informal)
[(QA)2: Question Answering with Questionable Assumptions](https://aclanthology.org/2023.acl-long.472) (Kim et al., ACL 2023)
ACL
- Najoung Kim, Phu Mon Htut, Samuel R. Bowman, and Jackson Petty. 2023. (QA)2: Question Answering with Questionable Assumptions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8466–8487, Toronto, Canada. Association for Computational Linguistics.