@inproceedings{morishita-etal-2024-jfld,
title = "{JFLD}: A {J}apanese Benchmark for Deductive Reasoning Based on Formal Logic",
author = "Morishita, Terufumi and
Yamaguchi, Atsuki and
Morio, Gaku and
Tomonari, Hikaru and
Imaichi, Osamu and
Sogawa, Yasuhiro",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.832",
pages = "9526--9535",
abstract = "Large language models (LLMs) have proficiently solved a broad range of tasks with their rich knowledge but often struggle with logical reasoning. To foster the research on logical reasoning, many benchmarks have been proposed so far. However, most of these benchmarks are limited to English, hindering the evaluation of LLMs specialized for each language. To address this, we propose **JFLD** (**J**apanese **F**ormal **L**ogic **D**eduction), a deductive reasoning benchmark for Japanese. JFLD assess whether LLMs can generate logical steps to (dis-)prove a given hypothesis based on a given set of facts. Its key features are assessing pure logical reasoning abilities isolated from knowledge and assessing various reasoning rules. We evaluate various Japanese LLMs and see that they are still poor at logical reasoning, thus highlighting a substantial need for future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morishita-etal-2024-jfld">
<titleInfo>
<title>JFLD: A Japanese Benchmark for Deductive Reasoning Based on Formal Logic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Terufumi</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaku</namePart>
<namePart type="family">Morio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hikaru</namePart>
<namePart type="family">Tomonari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osamu</namePart>
<namePart type="family">Imaichi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhiro</namePart>
<namePart type="family">Sogawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have proficiently solved a broad range of tasks with their rich knowledge but often struggle with logical reasoning. To foster the research on logical reasoning, many benchmarks have been proposed so far. However, most of these benchmarks are limited to English, hindering the evaluation of LLMs specialized for each language. To address this, we propose **JFLD** (**J**apanese **F**ormal **L**ogic **D**eduction), a deductive reasoning benchmark for Japanese. JFLD assess whether LLMs can generate logical steps to (dis-)prove a given hypothesis based on a given set of facts. Its key features are assessing pure logical reasoning abilities isolated from knowledge and assessing various reasoning rules. We evaluate various Japanese LLMs and see that they are still poor at logical reasoning, thus highlighting a substantial need for future research.</abstract>
<identifier type="citekey">morishita-etal-2024-jfld</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.832</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9526</start>
<end>9535</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JFLD: A Japanese Benchmark for Deductive Reasoning Based on Formal Logic
%A Morishita, Terufumi
%A Yamaguchi, Atsuki
%A Morio, Gaku
%A Tomonari, Hikaru
%A Imaichi, Osamu
%A Sogawa, Yasuhiro
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F morishita-etal-2024-jfld
%X Large language models (LLMs) have proficiently solved a broad range of tasks with their rich knowledge but often struggle with logical reasoning. To foster the research on logical reasoning, many benchmarks have been proposed so far. However, most of these benchmarks are limited to English, hindering the evaluation of LLMs specialized for each language. To address this, we propose **JFLD** (**J**apanese **F**ormal **L**ogic **D**eduction), a deductive reasoning benchmark for Japanese. JFLD assess whether LLMs can generate logical steps to (dis-)prove a given hypothesis based on a given set of facts. Its key features are assessing pure logical reasoning abilities isolated from knowledge and assessing various reasoning rules. We evaluate various Japanese LLMs and see that they are still poor at logical reasoning, thus highlighting a substantial need for future research.
%U https://aclanthology.org/2024.lrec-main.832
%P 9526-9535
Markdown (Informal)
[JFLD: A Japanese Benchmark for Deductive Reasoning Based on Formal Logic](https://aclanthology.org/2024.lrec-main.832) (Morishita et al., LREC-COLING 2024)
ACL
- Terufumi Morishita, Atsuki Yamaguchi, Gaku Morio, Hikaru Tomonari, Osamu Imaichi, and Yasuhiro Sogawa. 2024. JFLD: A Japanese Benchmark for Deductive Reasoning Based on Formal Logic. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9526–9535, Torino, Italia. ELRA and ICCL.