@inproceedings{junker-etal-2025-multimodal,
title = "Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?",
author = "Junker, Simeon and
Ali, Manar and
Koch, Larissa and
Zarrie{\ss}, Sina and
Buschmeier, Hendrik",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1236/",
doi = "10.18653/v1/2025.findings-acl.1236",
pages = "24101--24109",
ISBN = "979-8-89176-256-5",
abstract = "We investigate the linguistic abilities of multimodal large language models in reference resolution tasks featuring simple yet abstract visual stimuli, such as color patches and color grids. Although the task may not seem challenging for today{'}s language models, being straightforward for human dyads, we consider it to be a highly relevant probe of the pragmatic capabilities of MLLMs. Our results and analyses indeed suggest that basic pragmatic capabilities, such as context-dependent interpretation of color descriptions, still constitute major challenges for state-of-the-art MLLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="junker-etal-2025-multimodal">
<titleInfo>
<title>Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simeon</namePart>
<namePart type="family">Junker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manar</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Koch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Buschmeier</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>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>We investigate the linguistic abilities of multimodal large language models in reference resolution tasks featuring simple yet abstract visual stimuli, such as color patches and color grids. Although the task may not seem challenging for today’s language models, being straightforward for human dyads, we consider it to be a highly relevant probe of the pragmatic capabilities of MLLMs. Our results and analyses indeed suggest that basic pragmatic capabilities, such as context-dependent interpretation of color descriptions, still constitute major challenges for state-of-the-art MLLMs.</abstract>
<identifier type="citekey">junker-etal-2025-multimodal</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1236</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1236/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>24101</start>
<end>24109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?
%A Junker, Simeon
%A Ali, Manar
%A Koch, Larissa
%A Zarrieß, Sina
%A Buschmeier, Hendrik
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F junker-etal-2025-multimodal
%X We investigate the linguistic abilities of multimodal large language models in reference resolution tasks featuring simple yet abstract visual stimuli, such as color patches and color grids. Although the task may not seem challenging for today’s language models, being straightforward for human dyads, we consider it to be a highly relevant probe of the pragmatic capabilities of MLLMs. Our results and analyses indeed suggest that basic pragmatic capabilities, such as context-dependent interpretation of color descriptions, still constitute major challenges for state-of-the-art MLLMs.
%R 10.18653/v1/2025.findings-acl.1236
%U https://aclanthology.org/2025.findings-acl.1236/
%U https://doi.org/10.18653/v1/2025.findings-acl.1236
%P 24101-24109
Markdown (Informal)
[Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?](https://aclanthology.org/2025.findings-acl.1236/) (Junker et al., Findings 2025)
ACL