@inproceedings{cui-etal-2024-exploring,
title = "Exploring Defeasibility in Causal Reasoning",
author = "Cui, Shaobo and
Milikic, Lazar and
Feng, Yiyang and
Ismayilzada, Mete and
Paul, Debjit and
Bosselut, Antoine and
Faltings, Boi",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.384",
pages = "6433--6452",
abstract = "Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effect should increase or decrease with the incorporation of strengthening arguments (supporters) or weakening arguments (defeaters), respectively. However, existing works ignore defeasibility in causal reasoning and fail to evaluate existing causal strength metrics in defeasible settings. In this work, we present $\delta$-CAUSAL, the first benchmark dataset for studying defeasibility in causal reasoning. $\delta$-CAUSAL includes around 11K events spanning ten domains, featuring defeasible causality pairs, namely, cause-effect pairs accompanied by supporters and defeaters. We further show that current causal strength metrics fail to reflect the change of causal strength with the incorporation of supporters or defeaters in $\delta$-CAUSAL. To this end, we propose CESAR (Causal Embedding aSsociation with Attention Rating), a metric that measures causal strength based on token-level causal relationships. CESAR achieves a significant 69.7{\%} relative improvement over existing metrics, increasing from 47.2{\%} to 80.1{\%} in capturing the causal strength change brought by supporters and defeaters. We further demonstrate even Large Language Models (LLMs) like GPT-3.5 still lag 4.5 and 10.7 points behind humans in generating supporters and defeaters, emphasizing the challenge posed by $\delta$-CAUSAL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cui-etal-2024-exploring">
<titleInfo>
<title>Exploring Defeasibility in Causal Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaobo</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lazar</namePart>
<namePart type="family">Milikic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mete</namePart>
<namePart type="family">Ismayilzada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debjit</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boi</namePart>
<namePart type="family">Faltings</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>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effect should increase or decrease with the incorporation of strengthening arguments (supporters) or weakening arguments (defeaters), respectively. However, existing works ignore defeasibility in causal reasoning and fail to evaluate existing causal strength metrics in defeasible settings. In this work, we present δ-CAUSAL, the first benchmark dataset for studying defeasibility in causal reasoning. δ-CAUSAL includes around 11K events spanning ten domains, featuring defeasible causality pairs, namely, cause-effect pairs accompanied by supporters and defeaters. We further show that current causal strength metrics fail to reflect the change of causal strength with the incorporation of supporters or defeaters in δ-CAUSAL. To this end, we propose CESAR (Causal Embedding aSsociation with Attention Rating), a metric that measures causal strength based on token-level causal relationships. CESAR achieves a significant 69.7% relative improvement over existing metrics, increasing from 47.2% to 80.1% in capturing the causal strength change brought by supporters and defeaters. We further demonstrate even Large Language Models (LLMs) like GPT-3.5 still lag 4.5 and 10.7 points behind humans in generating supporters and defeaters, emphasizing the challenge posed by δ-CAUSAL.</abstract>
<identifier type="citekey">cui-etal-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.384</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>6433</start>
<end>6452</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Defeasibility in Causal Reasoning
%A Cui, Shaobo
%A Milikic, Lazar
%A Feng, Yiyang
%A Ismayilzada, Mete
%A Paul, Debjit
%A Bosselut, Antoine
%A Faltings, Boi
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F cui-etal-2024-exploring
%X Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effect should increase or decrease with the incorporation of strengthening arguments (supporters) or weakening arguments (defeaters), respectively. However, existing works ignore defeasibility in causal reasoning and fail to evaluate existing causal strength metrics in defeasible settings. In this work, we present δ-CAUSAL, the first benchmark dataset for studying defeasibility in causal reasoning. δ-CAUSAL includes around 11K events spanning ten domains, featuring defeasible causality pairs, namely, cause-effect pairs accompanied by supporters and defeaters. We further show that current causal strength metrics fail to reflect the change of causal strength with the incorporation of supporters or defeaters in δ-CAUSAL. To this end, we propose CESAR (Causal Embedding aSsociation with Attention Rating), a metric that measures causal strength based on token-level causal relationships. CESAR achieves a significant 69.7% relative improvement over existing metrics, increasing from 47.2% to 80.1% in capturing the causal strength change brought by supporters and defeaters. We further demonstrate even Large Language Models (LLMs) like GPT-3.5 still lag 4.5 and 10.7 points behind humans in generating supporters and defeaters, emphasizing the challenge posed by δ-CAUSAL.
%U https://aclanthology.org/2024.findings-acl.384
%P 6433-6452
Markdown (Informal)
[Exploring Defeasibility in Causal Reasoning](https://aclanthology.org/2024.findings-acl.384) (Cui et al., Findings 2024)
ACL
- Shaobo Cui, Lazar Milikic, Yiyang Feng, Mete Ismayilzada, Debjit Paul, Antoine Bosselut, and Boi Faltings. 2024. Exploring Defeasibility in Causal Reasoning. In Findings of the Association for Computational Linguistics ACL 2024, pages 6433–6452, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.