@inproceedings{liu-etal-2025-bridging,
title = "Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions",
author = "Liu, Zhe and
Kang, Taekyu and
Wang, Haoyu and
Alavi, Seyed Hossein and
Shwartz, Vered",
editor = "Frermann, Lea and
Stevenson, Mark",
booktitle = "Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.starsem-1.2/",
pages = "13--30",
ISBN = "979-8-89176-340-1",
abstract = "Generating diverse follow-up questions that uncover missing information remains challenging for conversational agents, particularly when they run on small, locally hosted models. To tackle this problem, we develop an information-gap{--}driven pipeline that contrasts the initial answer with an LLM-generated comprehensive answer, identifies the information gaps, and formulates gap-bridging follow-up questions. Applying the pipeline, we augment an existing dataset{--}FollowupQG{--}tenfold. Experiments show that models fine-tuned on the augmented dataset achieve significantly higher informativeness and diversity than variations trained on the original dataset. These findings indicate that our pipeline, which mirrors the human cognitive process of information seeking, provides an efficient distillation channel from state-of-the-art LLMs to smaller models, enabling resource-constrained conversational systems to generate more diverse and informative follow-up questions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-bridging">
<titleInfo>
<title>Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taekyu</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Alavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</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 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="family">Frermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Stevenson</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">979-8-89176-340-1</identifier>
</relatedItem>
<abstract>Generating diverse follow-up questions that uncover missing information remains challenging for conversational agents, particularly when they run on small, locally hosted models. To tackle this problem, we develop an information-gap–driven pipeline that contrasts the initial answer with an LLM-generated comprehensive answer, identifies the information gaps, and formulates gap-bridging follow-up questions. Applying the pipeline, we augment an existing dataset–FollowupQG–tenfold. Experiments show that models fine-tuned on the augmented dataset achieve significantly higher informativeness and diversity than variations trained on the original dataset. These findings indicate that our pipeline, which mirrors the human cognitive process of information seeking, provides an efficient distillation channel from state-of-the-art LLMs to smaller models, enabling resource-constrained conversational systems to generate more diverse and informative follow-up questions.</abstract>
<identifier type="citekey">liu-etal-2025-bridging</identifier>
<location>
<url>https://aclanthology.org/2025.starsem-1.2/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>13</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions
%A Liu, Zhe
%A Kang, Taekyu
%A Wang, Haoyu
%A Alavi, Seyed Hossein
%A Shwartz, Vered
%Y Frermann, Lea
%Y Stevenson, Mark
%S Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-340-1
%F liu-etal-2025-bridging
%X Generating diverse follow-up questions that uncover missing information remains challenging for conversational agents, particularly when they run on small, locally hosted models. To tackle this problem, we develop an information-gap–driven pipeline that contrasts the initial answer with an LLM-generated comprehensive answer, identifies the information gaps, and formulates gap-bridging follow-up questions. Applying the pipeline, we augment an existing dataset–FollowupQG–tenfold. Experiments show that models fine-tuned on the augmented dataset achieve significantly higher informativeness and diversity than variations trained on the original dataset. These findings indicate that our pipeline, which mirrors the human cognitive process of information seeking, provides an efficient distillation channel from state-of-the-art LLMs to smaller models, enabling resource-constrained conversational systems to generate more diverse and informative follow-up questions.
%U https://aclanthology.org/2025.starsem-1.2/
%P 13-30
Markdown (Informal)
[Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions](https://aclanthology.org/2025.starsem-1.2/) (Liu et al., *SEM 2025)
ACL