@inproceedings{sahay-etal-2025-ask,
title = "{ASK}: Aspects and Retrieval based Hybrid Clarification in Task Oriented Dialogue Systems",
author = "Sahay, Rishav and
Tekumalla, Lavanya Sita and
Aggarwal, Purav and
Jain, Arihant and
Saladi, Anoop",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.63/",
doi = "10.18653/v1/2025.acl-industry.63",
pages = "881--895",
ISBN = "979-8-89176-288-6",
abstract = "Ambiguous user queries pose a significant challenge in task-oriented dialogue systems relying on information retrieval. While Large Language Models (LLMs) have shown promise in generating clarification questions to tackle query ambiguity, they rely solely on the top-k retrieved documents for clarification which fails when ambiguity is too high to retrieve relevant documents in the first place. Traditional approaches lack principled mechanisms to determine when to use broad domain knowledge vs specific retrieved document context for clarification. We propose AsK, a novel hybrid approach that dynamically chooses between document-based or aspect-based clarification based on query ambiguity. Our approach requires no labeled clarification data and introduces: (1) Weakly-supervised Longformer-based ambiguity analysis, (2) Automated domain-specific aspect generation using clustering and LLMs and (3) LLM-powered clarification generation. AsK demonstrates significant improvements over baselines in both single-turn and multi-turn settings (recall@5 gain of {\textasciitilde}20{\%}) when evaluated on product troubleshooting and product search datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahay-etal-2025-ask">
<titleInfo>
<title>ASK: Aspects and Retrieval based Hybrid Clarification in Task Oriented Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rishav</namePart>
<namePart type="family">Sahay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lavanya</namePart>
<namePart type="given">Sita</namePart>
<namePart type="family">Tekumalla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Purav</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arihant</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Saladi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>Ambiguous user queries pose a significant challenge in task-oriented dialogue systems relying on information retrieval. While Large Language Models (LLMs) have shown promise in generating clarification questions to tackle query ambiguity, they rely solely on the top-k retrieved documents for clarification which fails when ambiguity is too high to retrieve relevant documents in the first place. Traditional approaches lack principled mechanisms to determine when to use broad domain knowledge vs specific retrieved document context for clarification. We propose AsK, a novel hybrid approach that dynamically chooses between document-based or aspect-based clarification based on query ambiguity. Our approach requires no labeled clarification data and introduces: (1) Weakly-supervised Longformer-based ambiguity analysis, (2) Automated domain-specific aspect generation using clustering and LLMs and (3) LLM-powered clarification generation. AsK demonstrates significant improvements over baselines in both single-turn and multi-turn settings (recall@5 gain of ~20%) when evaluated on product troubleshooting and product search datasets.</abstract>
<identifier type="citekey">sahay-etal-2025-ask</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.63</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.63/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>881</start>
<end>895</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASK: Aspects and Retrieval based Hybrid Clarification in Task Oriented Dialogue Systems
%A Sahay, Rishav
%A Tekumalla, Lavanya Sita
%A Aggarwal, Purav
%A Jain, Arihant
%A Saladi, Anoop
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F sahay-etal-2025-ask
%X Ambiguous user queries pose a significant challenge in task-oriented dialogue systems relying on information retrieval. While Large Language Models (LLMs) have shown promise in generating clarification questions to tackle query ambiguity, they rely solely on the top-k retrieved documents for clarification which fails when ambiguity is too high to retrieve relevant documents in the first place. Traditional approaches lack principled mechanisms to determine when to use broad domain knowledge vs specific retrieved document context for clarification. We propose AsK, a novel hybrid approach that dynamically chooses between document-based or aspect-based clarification based on query ambiguity. Our approach requires no labeled clarification data and introduces: (1) Weakly-supervised Longformer-based ambiguity analysis, (2) Automated domain-specific aspect generation using clustering and LLMs and (3) LLM-powered clarification generation. AsK demonstrates significant improvements over baselines in both single-turn and multi-turn settings (recall@5 gain of ~20%) when evaluated on product troubleshooting and product search datasets.
%R 10.18653/v1/2025.acl-industry.63
%U https://aclanthology.org/2025.acl-industry.63/
%U https://doi.org/10.18653/v1/2025.acl-industry.63
%P 881-895
Markdown (Informal)
[ASK: Aspects and Retrieval based Hybrid Clarification in Task Oriented Dialogue Systems](https://aclanthology.org/2025.acl-industry.63/) (Sahay et al., ACL 2025)
ACL