@inproceedings{wang-etal-2026-llms-capture,
title = "Do {LLM}s Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives",
author = "Wang, Yu and
Chersoni, Emmanuele and
Huang, Chu-Ren",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.461/",
pages = "10158--10174",
ISBN = "979-8-89176-390-6",
abstract = "Do large language models (LLMs) truly acquire embodied cognition and cultural conventions from text? We introduce demonstratives, fundamental spatial expressions like ``this/that'' in English and ``这/那'' in Chinese, as a novel probe for grounded knowledge. Using 6,400 responses from 320 native speakers, we establish a human baseline: English speakers reliably distinguish proximal{--}distal referents but struggle with perspective-taking, while Chinese speakers switch perspectives fluently but tolerate distal ambiguity. In contrast, five state-of-the-art LLMs fail to inherently understand the proximal{--}distal contrast and show no cultural differences, defaulting to English-centric reasoning. Our study contributes (i) demonstratives as a new lens for evaluating embodied cognition and cultural conventions, (ii) empirical evidence of cross-cultural asymmetries in human interpretation, (iii) a new perspective on the egocentric{--}sociocentric debate, showing both orientations coexist but vary across languages, and (iv) a call to address individual variation in future model design."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-llms-capture">
<titleInfo>
<title>Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Do large language models (LLMs) truly acquire embodied cognition and cultural conventions from text? We introduce demonstratives, fundamental spatial expressions like “this/that” in English and “这/那” in Chinese, as a novel probe for grounded knowledge. Using 6,400 responses from 320 native speakers, we establish a human baseline: English speakers reliably distinguish proximal–distal referents but struggle with perspective-taking, while Chinese speakers switch perspectives fluently but tolerate distal ambiguity. In contrast, five state-of-the-art LLMs fail to inherently understand the proximal–distal contrast and show no cultural differences, defaulting to English-centric reasoning. Our study contributes (i) demonstratives as a new lens for evaluating embodied cognition and cultural conventions, (ii) empirical evidence of cross-cultural asymmetries in human interpretation, (iii) a new perspective on the egocentric–sociocentric debate, showing both orientations coexist but vary across languages, and (iv) a call to address individual variation in future model design.</abstract>
<identifier type="citekey">wang-etal-2026-llms-capture</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.461/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>10158</start>
<end>10174</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives
%A Wang, Yu
%A Chersoni, Emmanuele
%A Huang, Chu-Ren
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wang-etal-2026-llms-capture
%X Do large language models (LLMs) truly acquire embodied cognition and cultural conventions from text? We introduce demonstratives, fundamental spatial expressions like “this/that” in English and “这/那” in Chinese, as a novel probe for grounded knowledge. Using 6,400 responses from 320 native speakers, we establish a human baseline: English speakers reliably distinguish proximal–distal referents but struggle with perspective-taking, while Chinese speakers switch perspectives fluently but tolerate distal ambiguity. In contrast, five state-of-the-art LLMs fail to inherently understand the proximal–distal contrast and show no cultural differences, defaulting to English-centric reasoning. Our study contributes (i) demonstratives as a new lens for evaluating embodied cognition and cultural conventions, (ii) empirical evidence of cross-cultural asymmetries in human interpretation, (iii) a new perspective on the egocentric–sociocentric debate, showing both orientations coexist but vary across languages, and (iv) a call to address individual variation in future model design.
%U https://aclanthology.org/2026.acl-long.461/
%P 10158-10174
Markdown (Informal)
[Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives](https://aclanthology.org/2026.acl-long.461/) (Wang et al., ACL 2026)
ACL