@inproceedings{tsuchida-etal-2026-empirical,
title = "An Empirical Study on Improving an {LLM}s based Interviewer Against Human Interviewees",
author = "Tsuchida, Rikuto and
Hasegawa, Ryo and
Sonoda, Tetsuya and
Utsuro, Takehito",
editor = "Suglia, Alessandro and
Giulianelli, Mario and
Schlangen, David and
Bernardi, Raffaella and
Fern{\'a}ndez, Raquel and
Hakimov, Sherzod and
McCallum, Sabrina and
Mazzaccara, Davide and
Le, Dieu-Thu and
Lemon, Oliver and
Koller, Alexander",
booktitle = "The Proceedings of Improving Language Models through Learning from Dialogue Game Interaction",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.lmplayschool-1.8/",
pages = "97--109",
ISBN = "979-8-89176-467-5",
abstract = "This paper presents a semi-structured interview system composed of multiple LLM components, in which an LLM-based interviewer conducts dialogue and another LLM estimates interviewee persona attributes from the dialogue history and dynamically updated slot information. The system prioritizes questions related to important yet unconfirmed attributes to support efficient interviews. We evaluate persona attribute estimation performance when interviewing both human participants and an LLM-based pseudo interviewee under zero-shot and few-shot prompting conditions. Experiments across three domains (IT engineer, store staff, and school teacher) with a total of 39 interviews show that persona attribute estimation is more challenging for human interviewees than for the LLM pseudo interviewee under zero-shot prompting. However, introducing few-shot prompting consistently improves estimation performance for human interviewees, primarily by increasing recall. On the other hand, its effect on the LLM pseudo interviewee is mixed across domains. A case study confirms, through case-based analysis, that persona attribute estimation improves when illustrative examples are provided."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsuchida-etal-2026-empirical">
<titleInfo>
<title>An Empirical Study on Improving an LLMs based Interviewer Against Human Interviewees</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rikuto</namePart>
<namePart type="family">Tsuchida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Tetsuya</namePart>
<namePart type="family">Sonoda</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>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The Proceedings of Improving Language Models through Learning from Dialogue Game Interaction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Suglia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Giulianelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sherzod</namePart>
<namePart type="family">Hakimov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Mazzaccara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieu-Thu</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-467-5</identifier>
</relatedItem>
<abstract>This paper presents a semi-structured interview system composed of multiple LLM components, in which an LLM-based interviewer conducts dialogue and another LLM estimates interviewee persona attributes from the dialogue history and dynamically updated slot information. The system prioritizes questions related to important yet unconfirmed attributes to support efficient interviews. We evaluate persona attribute estimation performance when interviewing both human participants and an LLM-based pseudo interviewee under zero-shot and few-shot prompting conditions. Experiments across three domains (IT engineer, store staff, and school teacher) with a total of 39 interviews show that persona attribute estimation is more challenging for human interviewees than for the LLM pseudo interviewee under zero-shot prompting. However, introducing few-shot prompting consistently improves estimation performance for human interviewees, primarily by increasing recall. On the other hand, its effect on the LLM pseudo interviewee is mixed across domains. A case study confirms, through case-based analysis, that persona attribute estimation improves when illustrative examples are provided.</abstract>
<identifier type="citekey">tsuchida-etal-2026-empirical</identifier>
<location>
<url>https://aclanthology.org/2026.lmplayschool-1.8/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>97</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Study on Improving an LLMs based Interviewer Against Human Interviewees
%A Tsuchida, Rikuto
%A Hasegawa, Ryo
%A Sonoda, Tetsuya
%A Utsuro, Takehito
%Y Suglia, Alessandro
%Y Giulianelli, Mario
%Y Schlangen, David
%Y Bernardi, Raffaella
%Y Fernández, Raquel
%Y Hakimov, Sherzod
%Y McCallum, Sabrina
%Y Mazzaccara, Davide
%Y Le, Dieu-Thu
%Y Lemon, Oliver
%Y Koller, Alexander
%S The Proceedings of Improving Language Models through Learning from Dialogue Game Interaction
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-467-5
%F tsuchida-etal-2026-empirical
%X This paper presents a semi-structured interview system composed of multiple LLM components, in which an LLM-based interviewer conducts dialogue and another LLM estimates interviewee persona attributes from the dialogue history and dynamically updated slot information. The system prioritizes questions related to important yet unconfirmed attributes to support efficient interviews. We evaluate persona attribute estimation performance when interviewing both human participants and an LLM-based pseudo interviewee under zero-shot and few-shot prompting conditions. Experiments across three domains (IT engineer, store staff, and school teacher) with a total of 39 interviews show that persona attribute estimation is more challenging for human interviewees than for the LLM pseudo interviewee under zero-shot prompting. However, introducing few-shot prompting consistently improves estimation performance for human interviewees, primarily by increasing recall. On the other hand, its effect on the LLM pseudo interviewee is mixed across domains. A case study confirms, through case-based analysis, that persona attribute estimation improves when illustrative examples are provided.
%U https://aclanthology.org/2026.lmplayschool-1.8/
%P 97-109
Markdown (Informal)
[An Empirical Study on Improving an LLMs based Interviewer Against Human Interviewees](https://aclanthology.org/2026.lmplayschool-1.8/) (Tsuchida et al., LM Playschool 2026)
ACL