@inproceedings{keizer-etal-2026-modular,
title = "A Modular Approach to Conversational Object Grounding in 3{D} Scenes Using {VLM}s and Prompt Chaining",
author = "Keizer, Simon and
Li, Mohan and
Farag, Youmna and
Stoyanchev, Svetlana and
Doddipatla, Rama",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.74/",
pages = "1049--1074",
ISBN = "979-8-89176-478-1",
abstract = "We introduce Conversational Object Grounding, a new task in which an agent must identify a target object in a complex 3D scene by engaging in natural language dialogue with a user who knows the target. It extends multimodal reference resolution on a single referring expression to conversations over multiple turns, combining it with clarification question generation and answer understanding to resolve ambiguities. For this task, we propose a zero-shot modular approach that combines the reference resolution, object captioning, and dialogue capabilities of foundation models, using prompt chaining in conjunction with an image-grounded scene graph. Evaluations on a new benchmark constructed with 3D scenes from ScanNet show that the proposed modular approach outperforms end-to-end baselines in terms of both grounding performance (up to 13{\%} improvement) and image processing cost (up to 63{\%} reduction)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keizer-etal-2026-modular">
<titleInfo>
<title>A Modular Approach to Conversational Object Grounding in 3D Scenes Using VLMs and Prompt Chaining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Keizer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youmna</namePart>
<namePart type="family">Farag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Stoyanchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rama</namePart>
<namePart type="family">Doddipatla</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 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</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">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>We introduce Conversational Object Grounding, a new task in which an agent must identify a target object in a complex 3D scene by engaging in natural language dialogue with a user who knows the target. It extends multimodal reference resolution on a single referring expression to conversations over multiple turns, combining it with clarification question generation and answer understanding to resolve ambiguities. For this task, we propose a zero-shot modular approach that combines the reference resolution, object captioning, and dialogue capabilities of foundation models, using prompt chaining in conjunction with an image-grounded scene graph. Evaluations on a new benchmark constructed with 3D scenes from ScanNet show that the proposed modular approach outperforms end-to-end baselines in terms of both grounding performance (up to 13% improvement) and image processing cost (up to 63% reduction).</abstract>
<identifier type="citekey">keizer-etal-2026-modular</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.74/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1049</start>
<end>1074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Modular Approach to Conversational Object Grounding in 3D Scenes Using VLMs and Prompt Chaining
%A Keizer, Simon
%A Li, Mohan
%A Farag, Youmna
%A Stoyanchev, Svetlana
%A Doddipatla, Rama
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F keizer-etal-2026-modular
%X We introduce Conversational Object Grounding, a new task in which an agent must identify a target object in a complex 3D scene by engaging in natural language dialogue with a user who knows the target. It extends multimodal reference resolution on a single referring expression to conversations over multiple turns, combining it with clarification question generation and answer understanding to resolve ambiguities. For this task, we propose a zero-shot modular approach that combines the reference resolution, object captioning, and dialogue capabilities of foundation models, using prompt chaining in conjunction with an image-grounded scene graph. Evaluations on a new benchmark constructed with 3D scenes from ScanNet show that the proposed modular approach outperforms end-to-end baselines in terms of both grounding performance (up to 13% improvement) and image processing cost (up to 63% reduction).
%U https://aclanthology.org/2026.groundlm-1.74/
%P 1049-1074
Markdown (Informal)
[A Modular Approach to Conversational Object Grounding in 3D Scenes Using VLMs and Prompt Chaining](https://aclanthology.org/2026.groundlm-1.74/) (Keizer et al., GroundLM 2026)
ACL