@inproceedings{son-etal-2025-curiosity,
title = "From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions",
author = "Son, Geonyeong and
Lee, Jaeyoung and
Kim, Misuk",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.202/",
doi = "10.18653/v1/2025.findings-naacl.202",
pages = "3649--3664",
ISBN = "979-8-89176-195-7",
abstract = "Humans attempt to understand the real world by asking the fundamental question ``Why?'' when faced with incomprehensible situations in everyday life. Such why-questions provide essential knowledge that can help in understanding these situations. In this study, we conducted an end-to-end process to verify the utility of consecutive why-questions, from constructing a large language model (LLM)-based dataset to performing quantitative evaluation and analysis. Firstly, we created a WHY-Chain dataset, consisting of answers generated by an LLM in response to chain-of-why-questions, including a validity check. We also incorporated objectives that effectively capture the ``consecutive'' characteristic of the data. Using the WHY-Chain dataset and two types of self-supervised objectives, we trained the pre-trained model. As a result, the refined model demonstrated improved performance on downstream tasks that require commonsense reasoning. Additionally, we conducted various ablation studies to assess the impact of different factors, confirming the scalability of the proposed approach. Lastly, we confirmed the consistency of the logical information by reasoning chain analysis of the answers generated from consecutive why-questions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="son-etal-2025-curiosity">
<titleInfo>
<title>From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geonyeong</namePart>
<namePart type="family">Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaeyoung</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Misuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Humans attempt to understand the real world by asking the fundamental question “Why?” when faced with incomprehensible situations in everyday life. Such why-questions provide essential knowledge that can help in understanding these situations. In this study, we conducted an end-to-end process to verify the utility of consecutive why-questions, from constructing a large language model (LLM)-based dataset to performing quantitative evaluation and analysis. Firstly, we created a WHY-Chain dataset, consisting of answers generated by an LLM in response to chain-of-why-questions, including a validity check. We also incorporated objectives that effectively capture the “consecutive” characteristic of the data. Using the WHY-Chain dataset and two types of self-supervised objectives, we trained the pre-trained model. As a result, the refined model demonstrated improved performance on downstream tasks that require commonsense reasoning. Additionally, we conducted various ablation studies to assess the impact of different factors, confirming the scalability of the proposed approach. Lastly, we confirmed the consistency of the logical information by reasoning chain analysis of the answers generated from consecutive why-questions.</abstract>
<identifier type="citekey">son-etal-2025-curiosity</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.202</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.202/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3649</start>
<end>3664</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions
%A Son, Geonyeong
%A Lee, Jaeyoung
%A Kim, Misuk
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F son-etal-2025-curiosity
%X Humans attempt to understand the real world by asking the fundamental question “Why?” when faced with incomprehensible situations in everyday life. Such why-questions provide essential knowledge that can help in understanding these situations. In this study, we conducted an end-to-end process to verify the utility of consecutive why-questions, from constructing a large language model (LLM)-based dataset to performing quantitative evaluation and analysis. Firstly, we created a WHY-Chain dataset, consisting of answers generated by an LLM in response to chain-of-why-questions, including a validity check. We also incorporated objectives that effectively capture the “consecutive” characteristic of the data. Using the WHY-Chain dataset and two types of self-supervised objectives, we trained the pre-trained model. As a result, the refined model demonstrated improved performance on downstream tasks that require commonsense reasoning. Additionally, we conducted various ablation studies to assess the impact of different factors, confirming the scalability of the proposed approach. Lastly, we confirmed the consistency of the logical information by reasoning chain analysis of the answers generated from consecutive why-questions.
%R 10.18653/v1/2025.findings-naacl.202
%U https://aclanthology.org/2025.findings-naacl.202/
%U https://doi.org/10.18653/v1/2025.findings-naacl.202
%P 3649-3664
Markdown (Informal)
[From Curiosity to Clarity : Exploring the Impact of Consecutive Why-Questions](https://aclanthology.org/2025.findings-naacl.202/) (Son et al., Findings 2025)
ACL