Culture fundamentally shapes people's reasoning, behavior, and communication. Generative artificial intelligence (AI) technologies may cause a shift towards a dominant culture. As people increasingly use AI to expedite and even automate various professional and personal tasks, cultural values embedded in AI models may bias authentic expression. We audit large language models for cultural bias, comparing their responses to nationally representative survey data, and evaluate country-specific prompting as a mitigation strategy. We find that GPT-4, 3.5 and 3 exhibit cultural values resembling English-speaking and Protestant European countries. Our mitigation strategy reduces cultural bias in recent models but not for all countries/territories. To avoid cultural bias in generative AI, especially in high-stakes contexts, we suggest using culture matching and ongoing cultural audits.

翻译：文化从根本上塑造了人类的推理、行为与交流方式。生成式人工智能技术可能导致主流文化的偏向。随着人们越来越依赖人工智能来加速甚至自动化各种专业及个人任务，嵌入在AI模型中的文化价值观可能会扭曲真实的表达。我们对大语言模型进行文化偏见审计，将其响应与全国代表性调查数据进行对比，并评估以国家/地区特定提示作为缓解策略的效果。研究发现，GPT-4、3.5和3展现出的文化价值观与英语国家和新教欧洲国家相似。我们的缓解策略减少了近期模型中的文化偏见，但并非对所有国家/地区都有效。为避免生成式人工智能中的文化偏见——尤其是在高风险场景中——我们建议采用文化匹配和持续性文化审计。