<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-meetingtom">
    <titleInfo>
        <title>MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ziyi</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuhang</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dongxu</namePart>
        <namePart type="family">Piao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xingyu</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tianhui</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Miao</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Theory of Mind (ToM), the ability to infer others’ beliefs, intentions, and states of knowledge, is central to social interaction, yet remains challenging for current Multimodal Large Language Models (MLLMs), especially in multi-party meetings where cues are distributed across speech and behavior. Existing multimodal ToM benchmarks mainly focus on video-grounded question answering over overt, externally verifiable signals, and provide limited coverage of nuanced social states and group dynamics. We introduce MeetingToM, a benchmark for complex social behavior reasoning in naturalistic multi-party meetings. MeetingToM targets meeting-specific phenomena such as pseudo-consensus, where apparent agreement co-occurs with cues of dissent under social pressure. The benchmark is hierarchically organized to evaluate ToM at increasing levels of social granularity, including (i) subject-level mental state prediction, (ii) dyadic-level addressee understanding, and (iii) group-level consensus reasoning. We provide a unified evaluation protocol and conduct systematic analyses of representative MLLMs, revealing persistent limitations in integrating non-verbal cues, predicting annotated attitudes, and distinguishing among consensus states. Our results highlight key challenges and establish MeetingToM as a testbed for advancing meeting-grounded ToM in multimodal models. Project page: https://oliviaziyi.github.io/MeetingToM-Project-Page/</abstract>
    <identifier type="citekey">wang-etal-2026-meetingtom</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.586/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>13396</start>
            <end>13422</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings
%A Wang, Ziyi
%A Wu, Yuhang
%A Piao, Dongxu
%A Liu, Xingyu
%A Zhou, Tianhui
%A Liu, Miao
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F wang-etal-2026-meetingtom
%X Theory of Mind (ToM), the ability to infer others’ beliefs, intentions, and states of knowledge, is central to social interaction, yet remains challenging for current Multimodal Large Language Models (MLLMs), especially in multi-party meetings where cues are distributed across speech and behavior. Existing multimodal ToM benchmarks mainly focus on video-grounded question answering over overt, externally verifiable signals, and provide limited coverage of nuanced social states and group dynamics. We introduce MeetingToM, a benchmark for complex social behavior reasoning in naturalistic multi-party meetings. MeetingToM targets meeting-specific phenomena such as pseudo-consensus, where apparent agreement co-occurs with cues of dissent under social pressure. The benchmark is hierarchically organized to evaluate ToM at increasing levels of social granularity, including (i) subject-level mental state prediction, (ii) dyadic-level addressee understanding, and (iii) group-level consensus reasoning. We provide a unified evaluation protocol and conduct systematic analyses of representative MLLMs, revealing persistent limitations in integrating non-verbal cues, predicting annotated attitudes, and distinguishing among consensus states. Our results highlight key challenges and establish MeetingToM as a testbed for advancing meeting-grounded ToM in multimodal models. Project page: https://oliviaziyi.github.io/MeetingToM-Project-Page/
%U https://aclanthology.org/2026.emnlp-main.586/
%P 13396-13422

Markdown (Informal)

[MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings](https://aclanthology.org/2026.emnlp-main.586/) (Wang et al., EMNLP 2026)

• MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings (Wang et al., EMNLP 2026)

ACL

• Ziyi Wang, Yuhang Wu, Dongxu Piao, Xingyu Liu, Tianhui Zhou, and Miao Liu. 2026. MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 13396–13422, Budapest, Hungary. Association for Computational Linguistics.