Beyond Instrumental and Substitutive Paradigms: Introducing Machine Culture as an Emergent Phenomenon in Large Language Models
Preprint
Abstract
Recent scholarship typically characterizes Large Language Models (LLMs) through either an \textit{Instrumental Paradigm} (viewing models as reflections of their developers' culture) or a \textit{Substitutive Paradigm} (viewing models as bilingual proxies that switch cultural frames based on language). This study challenges these anthropomorphic frameworks by proposing \textbf{Machine Culture} as an emergent, distinct phenomenon. We employed a 2 (Model Origin: US vs. China) $\times$ 2 (Prompt Language: English vs. Chinese) factorial design across eight multimodal tasks, uniquely incorporating image generation and interpretation to extend analysis beyond textual boundaries. Results revealed inconsistencies with both dominant paradigms: Model origin did not predict cultural alignment, with US models frequently exhibiting ``holistic'' traits typically associated with East Asian data. Similarly, prompt language did not trigger stable cultural frame-switching; instead, we observed \textbf{Cultural Reversal}, where English prompts paradoxically elicited higher contextual attention than Chinese prompts. Crucially, we identified a novel phenomenon termed \textbf{Service Persona Camouflage}: Reinforcement Learning from Human Feedback (RLHF) collapsed cultural variance in affective tasks into a hyper-positive, zero-variance ``helpful assistant'' persona. We conclude that LLMs do not simulate human culture but exhibit an emergent Machine Culture -- a probabilistic phenomenon shaped by \textit{superposition} in high-dimensional space and \textit{mode collapse} from safety alignment.
Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- A large-scale replication of scenario-based experiments in psychology and management using large language modelsNature Computational Science, 2025
- Cultural tendencies in generative AINature Human Behaviour, 2025
- Toward accurate psychological simulations: Investigating LLMs’ responses to personality and cultural variablesComputers in Human Behavior, 2025
- Large language models that replace human participants can harmfully misportray and flatten identity groupsNature Machine Intelligence, 2025
- Risk and prosocial behavioural cues elicit human-like response patterns from AI chatbotsScientific Reports, 2024
- Machine cultureNature Human Behaviour, 2023
- Probing the psychology of AI modelsProceedings of the National Academy of Sciences, 2023
- Cultural variation in affect valuation.Journal of Personality and Social Psychology, 2006
- Is It Culture or Is It Language? Examination of Language Effects in Cross-Cultural Research on Categorization.Journal of Personality and Social Psychology, 2004
- Culture and systems of thought: Holistic versus analytic cognition.Psychological Review, 2001