Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives

2026-04-28

AI Summary

This study investigates whether large language models (LLMs) can acquire embodied cognition and cultural variation through text, focusing on cross-linguistic spatial demonstratives such as English “this/that” and Chinese “这/那”. The authors construct a novel probing task comprising 6,400 native-speaker responses to establish a human performance baseline and evaluate mainstream LLMs on spatial reference and perspective-taking. Innovatively using demonstratives as probes, the work reveals asymmetries in human cross-cultural interpretation, reconciling theoretical tensions between egocentric and sociocentric accounts of spatial cognition. The findings demonstrate that current LLMs generally lack the ability to distinguish proximal from distal reference, exhibit an English-centric bias, and overlook cultural diversity—highlighting the critical need to incorporate individual and cultural variability into model design.

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 "zhè/nà" 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) a new task, based on 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.

Problem

• embodied cognition
• cultural variation
• demonstratives
• large language models
• cross-linguistic

Innovation

• demonstratives
• embodied cognition
• cultural variation
• cross-linguistic
• large language models