@inproceedings{zhang-choi-2025-clarify,
title = "Clarify When Necessary: Resolving Ambiguity Through Interaction with {LM}s",
author = "Zhang, Michael JQ and
Choi, Eunsol",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.306/",
doi = "10.18653/v1/2025.findings-naacl.306",
pages = "5526--5543",
ISBN = "979-8-89176-195-7",
abstract = "In this work, we explore the challenges of developing interactive assistants that resolve ambiguity by asking their users clarifying questions. Specifically, we develop a task-agnostic framework for evaluating a system{'}s ability to determine when to ask for clarification. Determining when to ask for clarification is a challenging task that requires systems to consider the demands of the individual user (i.e., how much they prioritize speed and usability versus carefulness) and the distribution of interpretations for a given request (i.e., whether an ambiguous request has one dominant, inferable interpretation). Using this framework, we evaluate systems for determining when to clarify across three NLP applications: QA, MT, and NLI. Finally, we introduce present a novel uncertainty estimation approach, IntentSim, that determines the utility of asking a clarifying question by estimating the entropy over user intents. Our method consistently outperforms existing uncertainty estimation approaches at identifying predictions that will benefit from clarification. Furthermore, we find that IntentSim is robust, demonstrating improvements across a wide range of NLP tasks and LMs. Together, our work lays foundation for further studies on clarifying interactions with LM assistants."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-choi-2025-clarify">
<titleInfo>
<title>Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">JQ</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>In this work, we explore the challenges of developing interactive assistants that resolve ambiguity by asking their users clarifying questions. Specifically, we develop a task-agnostic framework for evaluating a system’s ability to determine when to ask for clarification. Determining when to ask for clarification is a challenging task that requires systems to consider the demands of the individual user (i.e., how much they prioritize speed and usability versus carefulness) and the distribution of interpretations for a given request (i.e., whether an ambiguous request has one dominant, inferable interpretation). Using this framework, we evaluate systems for determining when to clarify across three NLP applications: QA, MT, and NLI. Finally, we introduce present a novel uncertainty estimation approach, IntentSim, that determines the utility of asking a clarifying question by estimating the entropy over user intents. Our method consistently outperforms existing uncertainty estimation approaches at identifying predictions that will benefit from clarification. Furthermore, we find that IntentSim is robust, demonstrating improvements across a wide range of NLP tasks and LMs. Together, our work lays foundation for further studies on clarifying interactions with LM assistants.</abstract>
<identifier type="citekey">zhang-choi-2025-clarify</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.306</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.306/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5526</start>
<end>5543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs
%A Zhang, Michael JQ
%A Choi, Eunsol
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F zhang-choi-2025-clarify
%X In this work, we explore the challenges of developing interactive assistants that resolve ambiguity by asking their users clarifying questions. Specifically, we develop a task-agnostic framework for evaluating a system’s ability to determine when to ask for clarification. Determining when to ask for clarification is a challenging task that requires systems to consider the demands of the individual user (i.e., how much they prioritize speed and usability versus carefulness) and the distribution of interpretations for a given request (i.e., whether an ambiguous request has one dominant, inferable interpretation). Using this framework, we evaluate systems for determining when to clarify across three NLP applications: QA, MT, and NLI. Finally, we introduce present a novel uncertainty estimation approach, IntentSim, that determines the utility of asking a clarifying question by estimating the entropy over user intents. Our method consistently outperforms existing uncertainty estimation approaches at identifying predictions that will benefit from clarification. Furthermore, we find that IntentSim is robust, demonstrating improvements across a wide range of NLP tasks and LMs. Together, our work lays foundation for further studies on clarifying interactions with LM assistants.
%R 10.18653/v1/2025.findings-naacl.306
%U https://aclanthology.org/2025.findings-naacl.306/
%U https://doi.org/10.18653/v1/2025.findings-naacl.306
%P 5526-5543
Markdown (Informal)
[Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs](https://aclanthology.org/2025.findings-naacl.306/) (Zhang & Choi, Findings 2025)
ACL