@inproceedings{arai-etal-2025-chakoshi,
title = "Chakoshi: A Customizable Guardrail for {LLM}s with a Focus on {J}apanese-Language Moderation",
author = "Arai, Kazuhiro and
Matsui, Ryota and
Miyama, Kenji and
Yamamoto, Yudai and
Shibamiya, Ren and
Sugimoto, Kaito and
Iwase, Yoshimasa",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.14/",
pages = "118--124",
abstract = "In this research, we developed and evaluated ``chakoshi'' an LLM guardrail model designed to address Japanese-specific nuances. chakoshi is a lightweight LLM that has been fine-tuned using multiple open datasets and proprietary learning datasets. Based on gemma-2-9b, the chakoshi model achieved an average F1 score of 0.92 or higher across multiple test datasets, demonstrating superior performance compared to existing models. Additionally, we implemented a feature that allows customization of categories to be filtered using natural language, and confirmed its effectiveness through practical examples."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arai-etal-2025-chakoshi">
<titleInfo>
<title>Chakoshi: A Customizable Guardrail for LLMs with a Focus on Japanese-Language Moderation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuhiro</namePart>
<namePart type="family">Arai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryota</namePart>
<namePart type="family">Matsui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Miyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudai</namePart>
<namePart type="family">Yamamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ren</namePart>
<namePart type="family">Shibamiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaito</namePart>
<namePart type="family">Sugimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshimasa</namePart>
<namePart type="family">Iwase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this research, we developed and evaluated “chakoshi” an LLM guardrail model designed to address Japanese-specific nuances. chakoshi is a lightweight LLM that has been fine-tuned using multiple open datasets and proprietary learning datasets. Based on gemma-2-9b, the chakoshi model achieved an average F1 score of 0.92 or higher across multiple test datasets, demonstrating superior performance compared to existing models. Additionally, we implemented a feature that allows customization of categories to be filtered using natural language, and confirmed its effectiveness through practical examples.</abstract>
<identifier type="citekey">arai-etal-2025-chakoshi</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.14/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>118</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chakoshi: A Customizable Guardrail for LLMs with a Focus on Japanese-Language Moderation
%A Arai, Kazuhiro
%A Matsui, Ryota
%A Miyama, Kenji
%A Yamamoto, Yudai
%A Shibamiya, Ren
%A Sugimoto, Kaito
%A Iwase, Yoshimasa
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F arai-etal-2025-chakoshi
%X In this research, we developed and evaluated “chakoshi” an LLM guardrail model designed to address Japanese-specific nuances. chakoshi is a lightweight LLM that has been fine-tuned using multiple open datasets and proprietary learning datasets. Based on gemma-2-9b, the chakoshi model achieved an average F1 score of 0.92 or higher across multiple test datasets, demonstrating superior performance compared to existing models. Additionally, we implemented a feature that allows customization of categories to be filtered using natural language, and confirmed its effectiveness through practical examples.
%U https://aclanthology.org/2025.ranlp-1.14/
%P 118-124
Markdown (Informal)
[Chakoshi: A Customizable Guardrail for LLMs with a Focus on Japanese-Language Moderation](https://aclanthology.org/2025.ranlp-1.14/) (Arai et al., RANLP 2025)
ACL
- Kazuhiro Arai, Ryota Matsui, Kenji Miyama, Yudai Yamamoto, Ren Shibamiya, Kaito Sugimoto, and Yoshimasa Iwase. 2025. Chakoshi: A Customizable Guardrail for LLMs with a Focus on Japanese-Language Moderation. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 118–124, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.