@inproceedings{masano-etal-2026-constructing-japanese,
title = "Constructing a {J}apanese Claim Decomposition Dataset for Fact-Checking of {LLM}-Generated Texts",
author = "Masano, Miwa and
Keyaki, Ribeka and
Keyaki, Atsushi and
Minamoto, Rei and
Horio, Kaito and
Kiyomaru, Hirokazu and
Nakayama, Kouta and
Tachibana, Hideyuki and
Kawahara, Daisuke",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.186/",
doi = "10.63317/5nsactrpnuu6",
pages = "2362--2375",
abstract = "Since texts generated by large language models (LLMs) may contain misinformation (hallucinations), develop- ing fact-checking systems capable of assessing their veracity has become increasingly important. One of the mainstream approaches to fact-checking is the claim-based one, which first decomposes a generated text into claims, i.e., independent and atomic units of information. Each claim is then used as a query to retrieve supporting evidence, and a verdict is predicted for each claim-evidence pair. Conducting fact-checking at the claim level enhances the explainability of verification results. However, achieving highly accurate verification requires that the text be decomposed into claims at an appropriate level of granularity. To address this, we constructed a dataset for Japanese claim decomposition. As part of this dataset construction, we design detailed guidelines for claim decomposition, ensuring that the extracted claims are in a form useful for fact-checking and that the decomposition rules mitigate annotator variability. Quantitative evaluation confirmed that the constructed dataset is of high quality. Additionally, experiments on prompt-based claim decomposition using the constructed dataset demonstrated that adding high-quality few-shot examples and guidelines to prompts improved performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="masano-etal-2026-constructing-japanese">
<titleInfo>
<title>Constructing a Japanese Claim Decomposition Dataset for Fact-Checking of LLM-Generated Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miwa</namePart>
<namePart type="family">Masano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ribeka</namePart>
<namePart type="family">Keyaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Keyaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rei</namePart>
<namePart type="family">Minamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaito</namePart>
<namePart type="family">Horio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hirokazu</namePart>
<namePart type="family">Kiyomaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kouta</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideyuki</namePart>
<namePart type="family">Tachibana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Since texts generated by large language models (LLMs) may contain misinformation (hallucinations), develop- ing fact-checking systems capable of assessing their veracity has become increasingly important. One of the mainstream approaches to fact-checking is the claim-based one, which first decomposes a generated text into claims, i.e., independent and atomic units of information. Each claim is then used as a query to retrieve supporting evidence, and a verdict is predicted for each claim-evidence pair. Conducting fact-checking at the claim level enhances the explainability of verification results. However, achieving highly accurate verification requires that the text be decomposed into claims at an appropriate level of granularity. To address this, we constructed a dataset for Japanese claim decomposition. As part of this dataset construction, we design detailed guidelines for claim decomposition, ensuring that the extracted claims are in a form useful for fact-checking and that the decomposition rules mitigate annotator variability. Quantitative evaluation confirmed that the constructed dataset is of high quality. Additionally, experiments on prompt-based claim decomposition using the constructed dataset demonstrated that adding high-quality few-shot examples and guidelines to prompts improved performance.</abstract>
<identifier type="citekey">masano-etal-2026-constructing-japanese</identifier>
<identifier type="doi">10.63317/5nsactrpnuu6</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.186/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2362</start>
<end>2375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing a Japanese Claim Decomposition Dataset for Fact-Checking of LLM-Generated Texts
%A Masano, Miwa
%A Keyaki, Ribeka
%A Keyaki, Atsushi
%A Minamoto, Rei
%A Horio, Kaito
%A Kiyomaru, Hirokazu
%A Nakayama, Kouta
%A Tachibana, Hideyuki
%A Kawahara, Daisuke
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F masano-etal-2026-constructing-japanese
%X Since texts generated by large language models (LLMs) may contain misinformation (hallucinations), develop- ing fact-checking systems capable of assessing their veracity has become increasingly important. One of the mainstream approaches to fact-checking is the claim-based one, which first decomposes a generated text into claims, i.e., independent and atomic units of information. Each claim is then used as a query to retrieve supporting evidence, and a verdict is predicted for each claim-evidence pair. Conducting fact-checking at the claim level enhances the explainability of verification results. However, achieving highly accurate verification requires that the text be decomposed into claims at an appropriate level of granularity. To address this, we constructed a dataset for Japanese claim decomposition. As part of this dataset construction, we design detailed guidelines for claim decomposition, ensuring that the extracted claims are in a form useful for fact-checking and that the decomposition rules mitigate annotator variability. Quantitative evaluation confirmed that the constructed dataset is of high quality. Additionally, experiments on prompt-based claim decomposition using the constructed dataset demonstrated that adding high-quality few-shot examples and guidelines to prompts improved performance.
%R 10.63317/5nsactrpnuu6
%U https://aclanthology.org/2026.lrec-1.186/
%U https://doi.org/10.63317/5nsactrpnuu6
%P 2362-2375
Markdown (Informal)
[Constructing a Japanese Claim Decomposition Dataset for Fact-Checking of LLM-Generated Texts](https://aclanthology.org/2026.lrec-1.186/) (Masano et al., LREC 2026)
ACL
- Miwa Masano, Ribeka Keyaki, Atsushi Keyaki, Rei Minamoto, Kaito Horio, Hirokazu Kiyomaru, Kouta Nakayama, Hideyuki Tachibana, and Daisuke Kawahara. 2026. Constructing a Japanese Claim Decomposition Dataset for Fact-Checking of LLM-Generated Texts. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2362–2375, Palma de Mallorca, Spain. ELRA Language Resource Association.