<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasegawa-etal-2025-dialogue">
    <titleInfo>
        <title>A Dialogue System for Semi-Structured Interviews by LLMs and its Evaluation on Persona Information Collection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ryo</namePart>
        <namePart type="family">Hasegawa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yijie</namePart>
        <namePart type="family">Hua</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Takehito</namePart>
        <namePart type="family">Utsuro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ekai</namePart>
        <namePart type="family">Hashimoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mikio</namePart>
        <namePart type="family">Nakano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shun</namePart>
        <namePart type="family">Shiramatsu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="given">Ines</namePart>
            <namePart type="family">Torres</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yuki</namePart>
            <namePart type="family">Matsuda</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zoraida</namePart>
            <namePart type="family">Callejas</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arantza</namePart>
            <namePart type="family">del Pozo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="given">Fernando</namePart>
            <namePart type="family">D’Haro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bilbao, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-248-0</identifier>
    </relatedItem>
    <abstract>In this paper, we propose a dialogue control management framework using large language models for semi-structured interviews. Specifically, large language models are used to generate the interviewer’s utterances and to make conditional branching decisions based on the understanding of the interviewee’s responses. The framework enables flexible dialogue control in interview conversations by generating and updating slots and values according to interviewee answers. More importantly, we invented through LLMs’ prompt tuning the framework of accumulating the list of slots generated along the course of incrementing the number of interviewees through the semi-structured interviews. Evaluation results showed that the proposed approach of accumulating the list of generated slots throughout the semi-structured interviews outperform the baseline without accumulating generated slots in terms of the number of persona attributes and values collected through the semi-structured interview.</abstract>
    <identifier type="citekey">hasegawa-etal-2025-dialogue</identifier>
    <location>
        <url>https://aclanthology.org/2025.iwsds-1.5/</url>
    </location>
    <part>
        <date>2025-05</date>
        <extent unit="page">
            <start>39</start>
            <end>59</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Dialogue System for Semi-Structured Interviews by LLMs and its Evaluation on Persona Information Collection
%A Hasegawa, Ryo
%A Hua, Yijie
%A Utsuro, Takehito
%A Hashimoto, Ekai
%A Nakano, Mikio
%A Shiramatsu, Shun
%Y Torres, Maria Ines
%Y Matsuda, Yuki
%Y Callejas, Zoraida
%Y del Pozo, Arantza
%Y D’Haro, Luis Fernando
%S Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology
%D 2025
%8 May
%I Association for Computational Linguistics
%C Bilbao, Spain
%@ 979-8-89176-248-0
%F hasegawa-etal-2025-dialogue
%X In this paper, we propose a dialogue control management framework using large language models for semi-structured interviews. Specifically, large language models are used to generate the interviewer’s utterances and to make conditional branching decisions based on the understanding of the interviewee’s responses. The framework enables flexible dialogue control in interview conversations by generating and updating slots and values according to interviewee answers. More importantly, we invented through LLMs’ prompt tuning the framework of accumulating the list of slots generated along the course of incrementing the number of interviewees through the semi-structured interviews. Evaluation results showed that the proposed approach of accumulating the list of generated slots throughout the semi-structured interviews outperform the baseline without accumulating generated slots in terms of the number of persona attributes and values collected through the semi-structured interview.
%U https://aclanthology.org/2025.iwsds-1.5/
%P 39-59

Markdown (Informal)

[A Dialogue System for Semi-Structured Interviews by LLMs and its Evaluation on Persona Information Collection](https://aclanthology.org/2025.iwsds-1.5/) (Hasegawa et al., IWSDS 2025)

• A Dialogue System for Semi-Structured Interviews by LLMs and its Evaluation on Persona Information Collection (Hasegawa et al., IWSDS 2025)

ACL

• Ryo Hasegawa, Yijie Hua, Takehito Utsuro, Ekai Hashimoto, Mikio Nakano, and Shun Shiramatsu. 2025. A Dialogue System for Semi-Structured Interviews by LLMs and its Evaluation on Persona Information Collection. In Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, pages 39–59, Bilbao, Spain. Association for Computational Linguistics.