Social Caption: Evaluating Social Understanding in Multimodal Models

Leena Mathur; Bhaavanaa Thumu; Gaoussou Youssouf Kebe; Louis-Philippe Morency

Social Caption: Evaluating Social Understanding in Multimodal Models

Leena Mathur, Bhaavanaa Thumu, Gaoussou Youssouf Kebe, Louis-Philippe Morency

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce Social Caption, a framework grounded in interaction theory to evaluate social understanding abilities of MLLMs along three dimensions: Social Inference (SI), the ability to make accurate inferences about interactions; Holistic Social Analysis (HSA), the ability to generate comprehensive descriptions of interactions; Directed Social Analysis (DSA), the ability to generate relevant information from interactions. We analyze factors influencing model performance in social understanding, such as scale, architectural design, and spoken context. Experiments with MLLM judges demonstrate a path towards scaling automated evaluation of multimodal social understanding.

Anthology ID:: 2026.findings-emnlp.1613
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 34345–34370
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.1613/
DOI:
Bibkey:
Cite (ACL):: Leena Mathur, Bhaavanaa Thumu, Gaoussou Youssouf Kebe, and Louis-Philippe Morency. 2026. Social Caption: Evaluating Social Understanding in Multimodal Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 34345–34370, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Social Caption: Evaluating Social Understanding in Multimodal Models (Mathur et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.1613.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{mathur-etal-2026-social,
    title = "Social Caption: Evaluating Social Understanding in Multimodal Models",
    author = "Mathur, Leena  and
      Thumu, Bhaavanaa  and
      Kebe, Gaoussou Youssouf  and
      Morency, Louis-Philippe",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1613/",
    pages = "34345--34370",
    ISBN = "979-8-89176-462-0",
    abstract = "Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce Social Caption, a framework grounded in interaction theory to evaluate social understanding abilities of MLLMs along three dimensions: Social Inference (SI), the ability to make accurate inferences about interactions; Holistic Social Analysis (HSA), the ability to generate comprehensive descriptions of interactions; Directed Social Analysis (DSA), the ability to generate relevant information from interactions. We analyze factors influencing model performance in social understanding, such as scale, architectural design, and spoken context. Experiments with MLLM judges demonstrate a path towards scaling automated evaluation of multimodal social understanding."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mathur-etal-2026-social">
    <titleInfo>
        <title>Social Caption: Evaluating Social Understanding in Multimodal Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Leena</namePart>
        <namePart type="family">Mathur</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bhaavanaa</namePart>
        <namePart type="family">Thumu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gaoussou</namePart>
        <namePart type="given">Youssouf</namePart>
        <namePart type="family">Kebe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Louis-Philippe</namePart>
        <namePart type="family">Morency</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce Social Caption, a framework grounded in interaction theory to evaluate social understanding abilities of MLLMs along three dimensions: Social Inference (SI), the ability to make accurate inferences about interactions; Holistic Social Analysis (HSA), the ability to generate comprehensive descriptions of interactions; Directed Social Analysis (DSA), the ability to generate relevant information from interactions. We analyze factors influencing model performance in social understanding, such as scale, architectural design, and spoken context. Experiments with MLLM judges demonstrate a path towards scaling automated evaluation of multimodal social understanding.</abstract>
    <identifier type="citekey">mathur-etal-2026-social</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1613/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>34345</start>
            <end>34370</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Social Caption: Evaluating Social Understanding in Multimodal Models
%A Mathur, Leena
%A Thumu, Bhaavanaa
%A Kebe, Gaoussou Youssouf
%A Morency, Louis-Philippe
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F mathur-etal-2026-social
%X Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce Social Caption, a framework grounded in interaction theory to evaluate social understanding abilities of MLLMs along three dimensions: Social Inference (SI), the ability to make accurate inferences about interactions; Holistic Social Analysis (HSA), the ability to generate comprehensive descriptions of interactions; Directed Social Analysis (DSA), the ability to generate relevant information from interactions. We analyze factors influencing model performance in social understanding, such as scale, architectural design, and spoken context. Experiments with MLLM judges demonstrate a path towards scaling automated evaluation of multimodal social understanding.
%U https://aclanthology.org/2026.findings-emnlp.1613/
%P 34345-34370

Download as File

Markdown (Informal)

[Social Caption: Evaluating Social Understanding in Multimodal Models](https://aclanthology.org/2026.findings-emnlp.1613/) (Mathur et al., Findings 2026)

Social Caption: Evaluating Social Understanding in Multimodal Models (Mathur et al., Findings 2026)

ACL

Leena Mathur, Bhaavanaa Thumu, Gaoussou Youssouf Kebe, and Louis-Philippe Morency. 2026. Social Caption: Evaluating Social Understanding in Multimodal Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 34345–34370, Budapest, Hungary. Association for Computational Linguistics.