Related Experiment Video
Updated: Sep 18, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Cultural tendencies in generative AI
Jackson G Lu1, Lesley Luyang Song2,3, Lu Doris Zhang4
1MIT Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA, USA. lu18@mit.edu.
Abstract:
We show that generative artificial intelligence (AI) models-trained on textual data that are inherently cultural-exhibit cultural tendencies when used in different human languages. Here we focus on two foundational constructs in cultural psychology: social orientation and cognitive style. First, we analyse GPT's responses to a large set of measures in both Chinese and English. When used in Chinese (versus English), GPT exhibits a more interdependent (versus independent) social orientation and a more holistic (versus analytic) cognitive style. Second, we replicate these cultural tendencies in ERNIE, a popular generative AI model in China. Third, we demonstrate the real-world impact of these cultural tendencies. For example, when used in Chinese (versus English), GPT is more likely to recommend advertisements with an interdependent (versus independent) social orientation. Fourth, exploratory analyses suggest that cultural prompts (for example, prompting generative AI to assume the role of a Chinese person) can adjust these cultural tendencies.
Related Concept Videos
Non-equilibrium in the Cell
Automatic Processing and Automatic Social Behavior
Introduction to Cognitive Psychology
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
Implicit Personality Theories
Cognitivism
Previously dominated by behaviorism, which prioritized observable behaviors and largely ignored mental processes, psychology transformed in the 1950s. Cognitive psychologists argue that understanding how we think and process...
Cultural Influences on Personality

