@inproceedings{kondo-etal-2023-probing,
title = "Probing Physical Reasoning with Counter-Commonsense Context",
author = "Kondo, Kazushi and
Sugawara, Saku and
Aizawa, Akiko",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.53/",
doi = "10.18653/v1/2023.acl-short.53",
pages = "603--612",
abstract = "In this study, we create a CConS (Counter-commonsense Contextual Size comparison) dataset to investigate how physical commonsense affects the contextualized size comparison task; the proposed dataset consists of both contexts that fit physical commonsense and those that do not. This dataset tests the ability of language models to predict the size relationship between objects under various contexts generated from our curated noun list and templates. We measure the ability of several masked language models and encoder-decoder models. The results show that while large language models can use prepositions such as {\textquotedblleft}in{\textquotedblright} and {\textquotedblleft}into{\textquotedblright} in the provided context to infer size relationships, they fail to use verbs and thus make incorrect judgments led by their prior physical commonsense."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kondo-etal-2023-probing">
<titleInfo>
<title>Probing Physical Reasoning with Counter-Commonsense Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazushi</namePart>
<namePart type="family">Kondo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saku</namePart>
<namePart type="family">Sugawara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</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 2: Short 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>In this study, we create a CConS (Counter-commonsense Contextual Size comparison) dataset to investigate how physical commonsense affects the contextualized size comparison task; the proposed dataset consists of both contexts that fit physical commonsense and those that do not. This dataset tests the ability of language models to predict the size relationship between objects under various contexts generated from our curated noun list and templates. We measure the ability of several masked language models and encoder-decoder models. The results show that while large language models can use prepositions such as “in” and “into” in the provided context to infer size relationships, they fail to use verbs and thus make incorrect judgments led by their prior physical commonsense.</abstract>
<identifier type="citekey">kondo-etal-2023-probing</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.53</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.53/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>603</start>
<end>612</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing Physical Reasoning with Counter-Commonsense Context
%A Kondo, Kazushi
%A Sugawara, Saku
%A Aizawa, Akiko
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kondo-etal-2023-probing
%X In this study, we create a CConS (Counter-commonsense Contextual Size comparison) dataset to investigate how physical commonsense affects the contextualized size comparison task; the proposed dataset consists of both contexts that fit physical commonsense and those that do not. This dataset tests the ability of language models to predict the size relationship between objects under various contexts generated from our curated noun list and templates. We measure the ability of several masked language models and encoder-decoder models. The results show that while large language models can use prepositions such as “in” and “into” in the provided context to infer size relationships, they fail to use verbs and thus make incorrect judgments led by their prior physical commonsense.
%R 10.18653/v1/2023.acl-short.53
%U https://aclanthology.org/2023.acl-short.53/
%U https://doi.org/10.18653/v1/2023.acl-short.53
%P 603-612
Markdown (Informal)
[Probing Physical Reasoning with Counter-Commonsense Context](https://aclanthology.org/2023.acl-short.53/) (Kondo et al., ACL 2023)
- Probing Physical Reasoning with Counter-Commonsense Context (Kondo et al., ACL 2023)
ACL
- Kazushi Kondo, Saku Sugawara, and Akiko Aizawa. 2023. Probing Physical Reasoning with Counter-Commonsense Context. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 603–612, Toronto, Canada. Association for Computational Linguistics.