@inproceedings{onozeki-inaba-2025-enhancing,
title = "Enhancing Coherence and Interestingness in Knowledge-Grounded Dialogue Generation",
author = "Onozeki, Hiroki and
Inaba, Michimasa",
editor = "Flek, Lucie and
Narayan, Shashi and
Phương, L{\^e} Hồng and
Pei, Jiahuan",
booktitle = "Proceedings of the 18th International Natural Language Generation Conference",
month = oct,
year = "2025",
address = "Hanoi, Vietnam",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.inlg-main.1/",
pages = "1--19",
abstract = "Open-domain dialogue systems have been increasingly applied in various situations, with a growing need to improve user engagement. One effective approach is to generate responses based on interesting external knowledge using knowledge-grounded response generation models. However, relying solely on interestingness can lead to incoherent responses, potentially diminishing user engagement. This paper proposes a novel method for generating engaging responses while maintaining contextual coherence. Our approach leverages a pre-trained knowledge-grounded response generation model and modifies the knowledge selection process to enhance response coherence and interestingness without requiring additional training. First, knowledge candidates with high contextual relevance are retrieved. These candidates are then reranked based on their interestingness and used to generate the responses. Finally, the method detects dialogue breakdowns and regenerates responses as necessary to ensure coherence. We conducted experiments using the Wizard of Wikipedia dataset and two state-of-the-art response generation models. The results indicate that the proposed method improves both response coherence and interestingness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="onozeki-inaba-2025-enhancing">
<titleInfo>
<title>Enhancing Coherence and Interestingness in Knowledge-Grounded Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Onozeki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michimasa</namePart>
<namePart type="family">Inaba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Natural Language Generation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashi</namePart>
<namePart type="family">Narayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lê</namePart>
<namePart type="given">Hồng</namePart>
<namePart type="family">Phương</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahuan</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hanoi, Vietnam</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open-domain dialogue systems have been increasingly applied in various situations, with a growing need to improve user engagement. One effective approach is to generate responses based on interesting external knowledge using knowledge-grounded response generation models. However, relying solely on interestingness can lead to incoherent responses, potentially diminishing user engagement. This paper proposes a novel method for generating engaging responses while maintaining contextual coherence. Our approach leverages a pre-trained knowledge-grounded response generation model and modifies the knowledge selection process to enhance response coherence and interestingness without requiring additional training. First, knowledge candidates with high contextual relevance are retrieved. These candidates are then reranked based on their interestingness and used to generate the responses. Finally, the method detects dialogue breakdowns and regenerates responses as necessary to ensure coherence. We conducted experiments using the Wizard of Wikipedia dataset and two state-of-the-art response generation models. The results indicate that the proposed method improves both response coherence and interestingness.</abstract>
<identifier type="citekey">onozeki-inaba-2025-enhancing</identifier>
<location>
<url>https://aclanthology.org/2025.inlg-main.1/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>1</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Coherence and Interestingness in Knowledge-Grounded Dialogue Generation
%A Onozeki, Hiroki
%A Inaba, Michimasa
%Y Flek, Lucie
%Y Narayan, Shashi
%Y Phương, Lê Hồng
%Y Pei, Jiahuan
%S Proceedings of the 18th International Natural Language Generation Conference
%D 2025
%8 October
%I Association for Computational Linguistics
%C Hanoi, Vietnam
%F onozeki-inaba-2025-enhancing
%X Open-domain dialogue systems have been increasingly applied in various situations, with a growing need to improve user engagement. One effective approach is to generate responses based on interesting external knowledge using knowledge-grounded response generation models. However, relying solely on interestingness can lead to incoherent responses, potentially diminishing user engagement. This paper proposes a novel method for generating engaging responses while maintaining contextual coherence. Our approach leverages a pre-trained knowledge-grounded response generation model and modifies the knowledge selection process to enhance response coherence and interestingness without requiring additional training. First, knowledge candidates with high contextual relevance are retrieved. These candidates are then reranked based on their interestingness and used to generate the responses. Finally, the method detects dialogue breakdowns and regenerates responses as necessary to ensure coherence. We conducted experiments using the Wizard of Wikipedia dataset and two state-of-the-art response generation models. The results indicate that the proposed method improves both response coherence and interestingness.
%U https://aclanthology.org/2025.inlg-main.1/
%P 1-19
Markdown (Informal)
[Enhancing Coherence and Interestingness in Knowledge-Grounded Dialogue Generation](https://aclanthology.org/2025.inlg-main.1/) (Onozeki & Inaba, INLG 2025)
ACL