@inproceedings{tsubokura-etal-2026-generation,
title = "Generation of Dialogue Breakdown Repair Utterance in Non-task Oriented Conversation",
author = "Tsubokura, Kazuya and
Iribe, Yurie and
Kitaoka, Norihide",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.38/",
pages = "553--558",
abstract = "Recent advances in large language models (LLMs) have significantly improved the response quality of dialogue systems. However, the issue of dialogue breakdowns where systems produce utterances that confuse users, such as those containing misinformation or lacking common sense still persists. Since such breakdowns can negatively affect users' impressions of dialogue systems, it is essential to appropriately repair the flow of conversation. Nevertheless, no existing method can robustly handle a wide range of breakdown types. To address this issue, this study aims to develop a dialogue breakdown repair generation system that can robustly handle various types of dialogue breakdowns. Specifically, we train an LLM using the Dialogue Breakdown Repair Corpus, which contains repair utterances corresponding to diverse breakdown scenarios. As a result, we construct a model specialized in generating repair utterances for various breakdown types and demonstrate that it achieves higher accuracy than existing models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsubokura-etal-2026-generation">
<titleInfo>
<title>Generation of Dialogue Breakdown Repair Utterance in Non-task Oriented Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuya</namePart>
<namePart type="family">Tsubokura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yurie</namePart>
<namePart type="family">Iribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norihide</namePart>
<namePart type="family">Kitaoka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in large language models (LLMs) have significantly improved the response quality of dialogue systems. However, the issue of dialogue breakdowns where systems produce utterances that confuse users, such as those containing misinformation or lacking common sense still persists. Since such breakdowns can negatively affect users’ impressions of dialogue systems, it is essential to appropriately repair the flow of conversation. Nevertheless, no existing method can robustly handle a wide range of breakdown types. To address this issue, this study aims to develop a dialogue breakdown repair generation system that can robustly handle various types of dialogue breakdowns. Specifically, we train an LLM using the Dialogue Breakdown Repair Corpus, which contains repair utterances corresponding to diverse breakdown scenarios. As a result, we construct a model specialized in generating repair utterances for various breakdown types and demonstrate that it achieves higher accuracy than existing models.</abstract>
<identifier type="citekey">tsubokura-etal-2026-generation</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.38/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>553</start>
<end>558</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generation of Dialogue Breakdown Repair Utterance in Non-task Oriented Conversation
%A Tsubokura, Kazuya
%A Iribe, Yurie
%A Kitaoka, Norihide
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F tsubokura-etal-2026-generation
%X Recent advances in large language models (LLMs) have significantly improved the response quality of dialogue systems. However, the issue of dialogue breakdowns where systems produce utterances that confuse users, such as those containing misinformation or lacking common sense still persists. Since such breakdowns can negatively affect users’ impressions of dialogue systems, it is essential to appropriately repair the flow of conversation. Nevertheless, no existing method can robustly handle a wide range of breakdown types. To address this issue, this study aims to develop a dialogue breakdown repair generation system that can robustly handle various types of dialogue breakdowns. Specifically, we train an LLM using the Dialogue Breakdown Repair Corpus, which contains repair utterances corresponding to diverse breakdown scenarios. As a result, we construct a model specialized in generating repair utterances for various breakdown types and demonstrate that it achieves higher accuracy than existing models.
%U https://aclanthology.org/2026.sigdial-1.38/
%P 553-558
Markdown (Informal)
[Generation of Dialogue Breakdown Repair Utterance in Non-task Oriented Conversation](https://aclanthology.org/2026.sigdial-1.38/) (Tsubokura et al., SIGDIAL 2026)
ACL