@inproceedings{seo-etal-2025-fq,
title = "{FQ}-Eval: Building Evaluation Dataset for User-centered Follow-up Question Generation",
author = "Seo, Sanghyun and
Kang, Bumsoo and
Lee, Dahm and
Kim, Jaeheon and
Shin, Joongbo and
Kim, Eui Soon and
Jeon, Kijeong",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.188/",
pages = "2811--2827",
ISBN = "979-8-89176-333-3",
abstract = "To effectively support users' goal achievement in chat-LLM services, providing user-centered follow-up questions is essential. Existing studies primarily focus on enhancing information-seeking or topical relevance, often missing how follow-up questions could satisfy users' intrinsic needs and conversational goals. To bridge this gap, we introduce FQ-Eval, a user-centered evaluation dataset designed for assessing follow-up question generation in chat-LLM services. FQ-Eval incorporates realistic chat-LLM usage scenarios and five distinct human-aligned criteria, each reflecting user expectations of effective follow-up questions. Experimental results show that FQ-Eval constructed through our approach clearly capture human-aligned criteria, enabling robust, human-aligned follow-up question generation evaluation of various models and services."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seo-etal-2025-fq">
<titleInfo>
<title>FQ-Eval: Building Evaluation Dataset for User-centered Follow-up Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanghyun</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bumsoo</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dahm</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaeheon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joongbo</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eui</namePart>
<namePart type="given">Soon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kijeong</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>To effectively support users’ goal achievement in chat-LLM services, providing user-centered follow-up questions is essential. Existing studies primarily focus on enhancing information-seeking or topical relevance, often missing how follow-up questions could satisfy users’ intrinsic needs and conversational goals. To bridge this gap, we introduce FQ-Eval, a user-centered evaluation dataset designed for assessing follow-up question generation in chat-LLM services. FQ-Eval incorporates realistic chat-LLM usage scenarios and five distinct human-aligned criteria, each reflecting user expectations of effective follow-up questions. Experimental results show that FQ-Eval constructed through our approach clearly capture human-aligned criteria, enabling robust, human-aligned follow-up question generation evaluation of various models and services.</abstract>
<identifier type="citekey">seo-etal-2025-fq</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.188/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2811</start>
<end>2827</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FQ-Eval: Building Evaluation Dataset for User-centered Follow-up Question Generation
%A Seo, Sanghyun
%A Kang, Bumsoo
%A Lee, Dahm
%A Kim, Jaeheon
%A Shin, Joongbo
%A Kim, Eui Soon
%A Jeon, Kijeong
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F seo-etal-2025-fq
%X To effectively support users’ goal achievement in chat-LLM services, providing user-centered follow-up questions is essential. Existing studies primarily focus on enhancing information-seeking or topical relevance, often missing how follow-up questions could satisfy users’ intrinsic needs and conversational goals. To bridge this gap, we introduce FQ-Eval, a user-centered evaluation dataset designed for assessing follow-up question generation in chat-LLM services. FQ-Eval incorporates realistic chat-LLM usage scenarios and five distinct human-aligned criteria, each reflecting user expectations of effective follow-up questions. Experimental results show that FQ-Eval constructed through our approach clearly capture human-aligned criteria, enabling robust, human-aligned follow-up question generation evaluation of various models and services.
%U https://aclanthology.org/2025.emnlp-industry.188/
%P 2811-2827
Markdown (Informal)
[FQ-Eval: Building Evaluation Dataset for User-centered Follow-up Question Generation](https://aclanthology.org/2025.emnlp-industry.188/) (Seo et al., EMNLP 2025)
ACL