@inproceedings{toda-etal-2026-hotate,
title = "{HOTATE}: A {J}apanese Dialogue Corpus Annotated with Responses of Private Thoughts and Public Statements",
author = "Toda, Yuko and
Maekawa, Daisuke and
Manabe, Kota and
Yoneyama, Eito and
Nonomura, Kanade and
Fujiwara, Yuki and
Kajiwara, Tomoyuki",
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-1.233/",
doi = "10.63317/3q6pji5z9zn7",
pages = "2987--2995",
abstract = "This study aims to reveal how accurately Large Language Models (LLMs) can deal with a speaker{'}s actual utterances and their true feelings behind them in Japanese dialogue. Speakers use not only private thoughts which express one{'}s true feelings and intentions, but also public statements which convey their intentions while considering the interlocutor{'}s feelings and social status. While public statements help to maintain interpersonal relationships, they can obscure the speaker{'}s true intention, potentially leading to misunderstandings. We extended existing Japanese dialogue corpora by annotating public statements and private thoughts responses for each dialogue in the corpora, and then evaluated LLMs' ability to classify and generate between these two types of expressions. The results of the classification task revealed that the current LLMs do not understand those expressions at all, and that training with our corpus can significantly improve the recognition performance. Furthermore, the results of the generation task demonstrated that generating private thoughts is more difficult than generating public statements, according to both automatic and human evaluations. We release our corpus, which contains 7,964 human-annotated dialogues."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toda-etal-2026-hotate">
<titleInfo>
<title>HOTATE: A Japanese Dialogue Corpus Annotated with Responses of Private Thoughts and Public Statements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuko</namePart>
<namePart type="family">Toda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Maekawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kota</namePart>
<namePart type="family">Manabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eito</namePart>
<namePart type="family">Yoneyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanade</namePart>
<namePart type="family">Nonomura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Fujiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</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>This study aims to reveal how accurately Large Language Models (LLMs) can deal with a speaker’s actual utterances and their true feelings behind them in Japanese dialogue. Speakers use not only private thoughts which express one’s true feelings and intentions, but also public statements which convey their intentions while considering the interlocutor’s feelings and social status. While public statements help to maintain interpersonal relationships, they can obscure the speaker’s true intention, potentially leading to misunderstandings. We extended existing Japanese dialogue corpora by annotating public statements and private thoughts responses for each dialogue in the corpora, and then evaluated LLMs’ ability to classify and generate between these two types of expressions. The results of the classification task revealed that the current LLMs do not understand those expressions at all, and that training with our corpus can significantly improve the recognition performance. Furthermore, the results of the generation task demonstrated that generating private thoughts is more difficult than generating public statements, according to both automatic and human evaluations. We release our corpus, which contains 7,964 human-annotated dialogues.</abstract>
<identifier type="citekey">toda-etal-2026-hotate</identifier>
<identifier type="doi">10.63317/3q6pji5z9zn7</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.233/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2987</start>
<end>2995</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HOTATE: A Japanese Dialogue Corpus Annotated with Responses of Private Thoughts and Public Statements
%A Toda, Yuko
%A Maekawa, Daisuke
%A Manabe, Kota
%A Yoneyama, Eito
%A Nonomura, Kanade
%A Fujiwara, Yuki
%A Kajiwara, Tomoyuki
%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 toda-etal-2026-hotate
%X This study aims to reveal how accurately Large Language Models (LLMs) can deal with a speaker’s actual utterances and their true feelings behind them in Japanese dialogue. Speakers use not only private thoughts which express one’s true feelings and intentions, but also public statements which convey their intentions while considering the interlocutor’s feelings and social status. While public statements help to maintain interpersonal relationships, they can obscure the speaker’s true intention, potentially leading to misunderstandings. We extended existing Japanese dialogue corpora by annotating public statements and private thoughts responses for each dialogue in the corpora, and then evaluated LLMs’ ability to classify and generate between these two types of expressions. The results of the classification task revealed that the current LLMs do not understand those expressions at all, and that training with our corpus can significantly improve the recognition performance. Furthermore, the results of the generation task demonstrated that generating private thoughts is more difficult than generating public statements, according to both automatic and human evaluations. We release our corpus, which contains 7,964 human-annotated dialogues.
%R 10.63317/3q6pji5z9zn7
%U https://aclanthology.org/2026.lrec-1.233/
%U https://doi.org/10.63317/3q6pji5z9zn7
%P 2987-2995
Markdown (Informal)
[HOTATE: A Japanese Dialogue Corpus Annotated with Responses of Private Thoughts and Public Statements](https://aclanthology.org/2026.lrec-1.233/) (Toda et al., LREC 2026)
ACL