arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2512.09772cs.CL

DeepSeek的WEIRD行为:大型语言模型的文化契合与提示语言和文化提示的影响

DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting

School of Data Science University of Virginia(数据科学学院 芝加哥大学)

James Luther, Donald Brown

AI总结:

研究探讨了大型语言模型在不同文化提示下的对齐行为,发现DeepSeek-V3和GPT-5在美文化下表现突出,而GPT-4在英文化下更接近中国,文化提示可调整这种对齐。

摘要:

文化是人类与人类互动的核心组成部分,在我们如何感知和与他人互动中起着至关重要的作用。大型语言模型(LLMs)在生成人类语气文本的有效性方面取得了显著进展,这极大地增加了人与计算机之间的互动量。随着这一领域的发展,这些类人代理的文化契合性成为一个重要的研究领域。我们的工作利用霍夫斯泰德的VSM13国际调查,了解以下模型的文化契合性:DeepSeek-V3、V3.1、GPT-4、GPT-4.1、GPT-4o和GPT-5。我们使用提示语言和文化提示的组合,一种利用系统提示将模型的对齐方式调整为特定国家的策略,将这些LLMs与美国和中国对齐。我们的结果表明,DeepSeek-V3、V3.1和OpenAI的GPT-5与美国调查响应有密切的对齐,即使使用文化提示或改变提示语言,也不达到与中国强或弱对齐。我们还发现,当用英语提示GPT-4时,其对齐更接近中国,但文化提示可以将这种对齐更接近美国。其他低成本模型GPT-4o和GPT-4.1对使用的提示语言(即英语或简体中文)和文化提示策略作出反应,以创建与美国和中国都可接受的对齐。

英文摘要:

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 the following models: DeepSeek-V3, V3.1, GPT-4, GPT-4.1, GPT-4o, and GPT-5. 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 these LLMs with the United States and China. 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑