@inproceedings{bhattacharya-di-eugenio-2026-clarvis,
title = "{C}lar{V}is: A Dataset of Clarification Requests and Grounding in Collaborative Data Visualization Dialogues",
author = "Bhattacharya, Abari and
Di Eugenio, Barbara",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.6/",
pages = "79--90",
abstract = "Clarification Requests (CRs) play a crucial role in human communication. However, existing datasets are often limited to single-turn clarifications or simulated tasks. We present a novel task-oriented dialogue dataset, ClarVis, of CRs collected from real-time multi-user collaborative data-exploration sessions, where users analyze data together while interacting with a visualization-generating conversational assistant. This dataset fills important gaps in current CR datasets by identifying naturally occurring CRs grounded by real-world modalities like hearing, vision, and actions in the physical environment. Our dataset includes 6.3K utterances across collaborative tasks, where each CR is annotated with a grounding modality - Auditory (A), Visual (V), or Kinesthetic (K) - that captures the context the clarification pertains to. Further, we establish benchmark tasks for CR identification and grounding-modality classification, and evaluate them with traditional machine learning models as well as instruction-tuned large language models. The results highlight both the learnability and the difficulty of these tasks, and position ClarVis as a useful resource for studying clarifications in collaborative dialogue settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharya-di-eugenio-2026-clarvis">
<titleInfo>
<title>ClarVis: A Dataset of Clarification Requests and Grounding in Collaborative Data Visualization Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abari</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Di Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Clarification Requests (CRs) play a crucial role in human communication. However, existing datasets are often limited to single-turn clarifications or simulated tasks. We present a novel task-oriented dialogue dataset, ClarVis, of CRs collected from real-time multi-user collaborative data-exploration sessions, where users analyze data together while interacting with a visualization-generating conversational assistant. This dataset fills important gaps in current CR datasets by identifying naturally occurring CRs grounded by real-world modalities like hearing, vision, and actions in the physical environment. Our dataset includes 6.3K utterances across collaborative tasks, where each CR is annotated with a grounding modality - Auditory (A), Visual (V), or Kinesthetic (K) - that captures the context the clarification pertains to. Further, we establish benchmark tasks for CR identification and grounding-modality classification, and evaluate them with traditional machine learning models as well as instruction-tuned large language models. The results highlight both the learnability and the difficulty of these tasks, and position ClarVis as a useful resource for studying clarifications in collaborative dialogue settings.</abstract>
<identifier type="citekey">bhattacharya-di-eugenio-2026-clarvis</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.6/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>79</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ClarVis: A Dataset of Clarification Requests and Grounding in Collaborative Data Visualization Dialogues
%A Bhattacharya, Abari
%A Di Eugenio, Barbara
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F bhattacharya-di-eugenio-2026-clarvis
%X Clarification Requests (CRs) play a crucial role in human communication. However, existing datasets are often limited to single-turn clarifications or simulated tasks. We present a novel task-oriented dialogue dataset, ClarVis, of CRs collected from real-time multi-user collaborative data-exploration sessions, where users analyze data together while interacting with a visualization-generating conversational assistant. This dataset fills important gaps in current CR datasets by identifying naturally occurring CRs grounded by real-world modalities like hearing, vision, and actions in the physical environment. Our dataset includes 6.3K utterances across collaborative tasks, where each CR is annotated with a grounding modality - Auditory (A), Visual (V), or Kinesthetic (K) - that captures the context the clarification pertains to. Further, we establish benchmark tasks for CR identification and grounding-modality classification, and evaluate them with traditional machine learning models as well as instruction-tuned large language models. The results highlight both the learnability and the difficulty of these tasks, and position ClarVis as a useful resource for studying clarifications in collaborative dialogue settings.
%U https://aclanthology.org/2026.sigdial-1.6/
%P 79-90
Markdown (Informal)
[ClarVis: A Dataset of Clarification Requests and Grounding in Collaborative Data Visualization Dialogues](https://aclanthology.org/2026.sigdial-1.6/) (Bhattacharya & Di Eugenio, SIGDIAL 2026)
ACL