<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dai-etal-2026-dont">
    <titleInfo>
        <title>Don’t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chongyuan</namePart>
        <namePart type="family">Dai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yaling</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shengeng</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinpeng</namePart>
        <namePart type="family">Hu</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 interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their communicative behavior across contexts. Despite recent advances in equipping Large Language Models (LLMs) with social understanding capabilities, existing approaches often model culture as a static demographic attribute, limiting their ability to accommodate hybrid and dynamically expressed communicative preferences. Therefore, in this paper, we propose **DyCAC**, a training-free framework that achieves fluid social alignment by incorporating **Dy**namic **C**ultural **A**daptation with continuous **C**ognitive tracking. Rather than inferring a fixed cultural identity, DyCAC models culturally relevant communicative preferences as a time-varying mixture of population-level cultural reference profiles. This reference-based representation is further calibrated using dialogue-style signals observed in the ongoing interaction, enabling the model to capture both composite cultural influences and turn-level shifts in communicative behavior. In parallel, a memory module driven by Theory of Mind (ToM) continuously tracks the cognitive states of the interlocutor. Extensive experiments on interactive social and cultural benchmarks demonstrate the superiority of our approach. The proposed framework outperforms existing baselines, exhibiting enhanced social intelligence and broad adaptability across varied multicultural contexts.</abstract>
    <identifier type="citekey">dai-etal-2026-dont</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1215</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1215/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>25738</start>
            <end>25759</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Don’t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social Understanding
%A Dai, Chongyuan
%A Shen, Yaling
%A Tang, Shengeng
%A Ma, Hui
%A Hu, Jinpeng
%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 dai-etal-2026-dont
%X Social interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their communicative behavior across contexts. Despite recent advances in equipping Large Language Models (LLMs) with social understanding capabilities, existing approaches often model culture as a static demographic attribute, limiting their ability to accommodate hybrid and dynamically expressed communicative preferences. Therefore, in this paper, we propose **DyCAC**, a training-free framework that achieves fluid social alignment by incorporating **Dy**namic **C**ultural **A**daptation with continuous **C**ognitive tracking. Rather than inferring a fixed cultural identity, DyCAC models culturally relevant communicative preferences as a time-varying mixture of population-level cultural reference profiles. This reference-based representation is further calibrated using dialogue-style signals observed in the ongoing interaction, enabling the model to capture both composite cultural influences and turn-level shifts in communicative behavior. In parallel, a memory module driven by Theory of Mind (ToM) continuously tracks the cognitive states of the interlocutor. Extensive experiments on interactive social and cultural benchmarks demonstrate the superiority of our approach. The proposed framework outperforms existing baselines, exhibiting enhanced social intelligence and broad adaptability across varied multicultural contexts.
%R 10.18653/2026.findings-emnlp.1215
%U https://aclanthology.org/2026.findings-emnlp.1215/
%U https://doi.org/10.18653/2026.findings-emnlp.1215
%P 25738-25759

Markdown (Informal)

[Don’t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social Understanding](https://aclanthology.org/2026.findings-emnlp.1215/) (Dai et al., Findings 2026)

• Don’t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social Understanding (Dai et al., Findings 2026)

ACL

• Chongyuan Dai, Yaling Shen, Shengeng Tang, Hui Ma, and Jinpeng Hu. 2026. Don’t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social Understanding. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 25738–25759, Budapest, Hungary. Association for Computational Linguistics.