@inproceedings{chen-etal-2026-smmu,
title = "{SMMU}: Benchmarking Social Intelligence of Multimodal Large Language Models",
author = "Chen, Gordon and
Huang, Ziqi and
Zeng, Ailing and
Mei, Chuhan and
Hu, Kairui and
Tong, Xin and
Liu, Ziwei",
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.2434/",
pages = "52242--52254",
ISBN = "979-8-89176-462-0",
abstract = "Recent Multimodal Large Language Models (MLLMs) have made rapid progress in video understanding, demonstrating strong performance across a wide range of perceptual and reasoning tasks. However, their Social Intelligence remains underexplored and difficult to evaluate. Existing benchmarks for social understanding suffer from two major limitations: they primarily evaluate short-horizon interactions and focus largely on explicit perceptual cues, such as facial expressions and speech sentiment. However, real-world social understanding often requires inferring implicit emotions, intentions, beliefs, and interpersonal dynamics from extended contextual interactions rather than isolated expressions or utterances. Consequently, robust evaluation of social intelligence requires long-horizon reasoning over complex social contexts. To address this gap, we introduce SMMU, a Massive Multimodal Social Understanding benchmark. SMMU comprises 264 long-form audiovisual scenes and 1519 question-answer pairs, to systematically evaluate each model across five social dimensions (Emotions, Intent, Knowledge State, Perspective, Relationships) and three cognitive tasks (Comprehension, Reasoning, Prediction). SMMU is designed to require models to integrate contextual evidence across extended interactions in order to interpret, reason about, and anticipate complex human behavior. Evaluating a suite of state-of-the-art MLLMs, we find that even the strongest models achieve only 0.43 Social Understanding Score compared to the average human baseline of 0.85, and 0.33 Social Agency Score compared to the human baseline of 0.78, revealing a substantial gap between current MLLMs and human social intelligence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-smmu">
<titleInfo>
<title>SMMU: Benchmarking Social Intelligence of Multimodal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gordon</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziqi</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ailing</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuhan</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kairui</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Liu</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>Recent Multimodal Large Language Models (MLLMs) have made rapid progress in video understanding, demonstrating strong performance across a wide range of perceptual and reasoning tasks. However, their Social Intelligence remains underexplored and difficult to evaluate. Existing benchmarks for social understanding suffer from two major limitations: they primarily evaluate short-horizon interactions and focus largely on explicit perceptual cues, such as facial expressions and speech sentiment. However, real-world social understanding often requires inferring implicit emotions, intentions, beliefs, and interpersonal dynamics from extended contextual interactions rather than isolated expressions or utterances. Consequently, robust evaluation of social intelligence requires long-horizon reasoning over complex social contexts. To address this gap, we introduce SMMU, a Massive Multimodal Social Understanding benchmark. SMMU comprises 264 long-form audiovisual scenes and 1519 question-answer pairs, to systematically evaluate each model across five social dimensions (Emotions, Intent, Knowledge State, Perspective, Relationships) and three cognitive tasks (Comprehension, Reasoning, Prediction). SMMU is designed to require models to integrate contextual evidence across extended interactions in order to interpret, reason about, and anticipate complex human behavior. Evaluating a suite of state-of-the-art MLLMs, we find that even the strongest models achieve only 0.43 Social Understanding Score compared to the average human baseline of 0.85, and 0.33 Social Agency Score compared to the human baseline of 0.78, revealing a substantial gap between current MLLMs and human social intelligence.</abstract>
<identifier type="citekey">chen-etal-2026-smmu</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2434/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52242</start>
<end>52254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SMMU: Benchmarking Social Intelligence of Multimodal Large Language Models
%A Chen, Gordon
%A Huang, Ziqi
%A Zeng, Ailing
%A Mei, Chuhan
%A Hu, Kairui
%A Tong, Xin
%A Liu, Ziwei
%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 chen-etal-2026-smmu
%X Recent Multimodal Large Language Models (MLLMs) have made rapid progress in video understanding, demonstrating strong performance across a wide range of perceptual and reasoning tasks. However, their Social Intelligence remains underexplored and difficult to evaluate. Existing benchmarks for social understanding suffer from two major limitations: they primarily evaluate short-horizon interactions and focus largely on explicit perceptual cues, such as facial expressions and speech sentiment. However, real-world social understanding often requires inferring implicit emotions, intentions, beliefs, and interpersonal dynamics from extended contextual interactions rather than isolated expressions or utterances. Consequently, robust evaluation of social intelligence requires long-horizon reasoning over complex social contexts. To address this gap, we introduce SMMU, a Massive Multimodal Social Understanding benchmark. SMMU comprises 264 long-form audiovisual scenes and 1519 question-answer pairs, to systematically evaluate each model across five social dimensions (Emotions, Intent, Knowledge State, Perspective, Relationships) and three cognitive tasks (Comprehension, Reasoning, Prediction). SMMU is designed to require models to integrate contextual evidence across extended interactions in order to interpret, reason about, and anticipate complex human behavior. Evaluating a suite of state-of-the-art MLLMs, we find that even the strongest models achieve only 0.43 Social Understanding Score compared to the average human baseline of 0.85, and 0.33 Social Agency Score compared to the human baseline of 0.78, revealing a substantial gap between current MLLMs and human social intelligence.
%U https://aclanthology.org/2026.findings-emnlp.2434/
%P 52242-52254
Markdown (Informal)
[SMMU: Benchmarking Social Intelligence of Multimodal Large Language Models](https://aclanthology.org/2026.findings-emnlp.2434/) (Chen et al., Findings 2026)
ACL