DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting
This addresses the problem of cultural bias in LLMs for users and developers, though it is incremental as it builds on existing cultural alignment research.
The study investigated the cultural alignment of large language models (LLMs) using Hofstede's VSM13 surveys, finding that models like DeepSeek-V3 and GPT-5 closely align with the United States but not China, while GPT-4 shows varied alignment depending on prompt language and cultural prompting.
Culture is a core component of human-to-human interaction and plays a vital role in how we perceive and interact with others. Advancements in the effectiveness of Large Language Models (LLMs) in generating human-sounding text have greatly increased the amount of human-to-computer interaction. As this field grows, the cultural alignment of these human-like agents becomes an important field of study. Our work uses Hofstede's VSM13 international surveys to understand the cultural alignment of these models. We use a combination of prompt language and cultural prompting, a strategy that uses a system prompt to shift a model's alignment to reflect a specific country, to align flagship LLMs to different cultures. Our results show that DeepSeek-V3, V3.1, and OpenAI's GPT-5 exhibit a close alignment with the survey responses of the United States and do not achieve a strong or soft alignment with China, even when using cultural prompts or changing the prompt language. We also find that GPT-4 exhibits an alignment closer to China when prompted in English, but cultural prompting is effective in shifting this alignment closer to the United States. Other low-cost models, GPT-4o and GPT-4.1, respond to the prompt language used (i.e., English or Simplified Chinese) and cultural prompting strategies to create acceptable alignments with both the United States and China.