@inproceedings{jeon-etal-2026-learning,
title = "Learning Diagnostic Clarifying Questions for Conversational Question Answering via Data-Efficient Dynamic Distillation",
author = "Jeon, Jihyeong and
Ryu, Cheol and
Kang, U",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.22/",
pages = "484--498",
ISBN = "979-8-89176-459-0",
abstract = "Given a query, how can a QA system ask an informative clarifying question to accurately answer it? Open-domain conversational question answering requires not only detecting when a query is ambiguous but also asking clarifying questions that efficiently uncover the latent intent of the user. However, existing approaches either rely on prompt-only clarify-or-answer decisions with limited robustness or distill clarification trajectories without explicitly modeling intent convergence. In this paper, we propose D4CQ (Data-Efficient Diagnosticity based Dynamic Distillation for Clarifying Question), a data-efficient framework for learning diagnostic clarifying questions through dynamic distillation. Our approach distills a structured refinement protocol, prioritizes informative clarifications via diagnosticity-based reweighting, and improves sample efficiency through hindsight relabeling. Empirical results demonstrates that D4CQ consistently outperforms strong baselines, while maintaining comparable interaction budgets. Our code is available at https://github.com/ddddcq/d4cq."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeon-etal-2026-learning">
<titleInfo>
<title>Learning Diagnostic Clarifying Questions for Conversational Question Answering via Data-Efficient Dynamic Distillation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jihyeong</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheol</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">U</namePart>
<namePart type="family">Kang</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Given a query, how can a QA system ask an informative clarifying question to accurately answer it? Open-domain conversational question answering requires not only detecting when a query is ambiguous but also asking clarifying questions that efficiently uncover the latent intent of the user. However, existing approaches either rely on prompt-only clarify-or-answer decisions with limited robustness or distill clarification trajectories without explicitly modeling intent convergence. In this paper, we propose D4CQ (Data-Efficient Diagnosticity based Dynamic Distillation for Clarifying Question), a data-efficient framework for learning diagnostic clarifying questions through dynamic distillation. Our approach distills a structured refinement protocol, prioritizes informative clarifications via diagnosticity-based reweighting, and improves sample efficiency through hindsight relabeling. Empirical results demonstrates that D4CQ consistently outperforms strong baselines, while maintaining comparable interaction budgets. Our code is available at https://github.com/ddddcq/d4cq.</abstract>
<identifier type="citekey">jeon-etal-2026-learning</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.22/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>484</start>
<end>498</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Diagnostic Clarifying Questions for Conversational Question Answering via Data-Efficient Dynamic Distillation
%A Jeon, Jihyeong
%A Ryu, Cheol
%A Kang, U.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F jeon-etal-2026-learning
%X Given a query, how can a QA system ask an informative clarifying question to accurately answer it? Open-domain conversational question answering requires not only detecting when a query is ambiguous but also asking clarifying questions that efficiently uncover the latent intent of the user. However, existing approaches either rely on prompt-only clarify-or-answer decisions with limited robustness or distill clarification trajectories without explicitly modeling intent convergence. In this paper, we propose D4CQ (Data-Efficient Diagnosticity based Dynamic Distillation for Clarifying Question), a data-efficient framework for learning diagnostic clarifying questions through dynamic distillation. Our approach distills a structured refinement protocol, prioritizes informative clarifications via diagnosticity-based reweighting, and improves sample efficiency through hindsight relabeling. Empirical results demonstrates that D4CQ consistently outperforms strong baselines, while maintaining comparable interaction budgets. Our code is available at https://github.com/ddddcq/d4cq.
%U https://aclanthology.org/2026.emnlp-main.22/
%P 484-498
Markdown (Informal)
[Learning Diagnostic Clarifying Questions for Conversational Question Answering via Data-Efficient Dynamic Distillation](https://aclanthology.org/2026.emnlp-main.22/) (Jeon et al., EMNLP 2026)
ACL