用AI生成虚拟文化群体，模拟不同社会的经济行为差异。
LLMs Model Non-WEIRD Populations: Experiments with Synthetic Cultural Agents
- 用大模型构建代表非西方群体的虚拟代理人。
- 虚拟代理行为与真实人类数据高度吻合，验证了方法有效性。
- 适合跨文化研究者快速生成可验证假设。
尽管跨文化经济行为研究至关重要，但对非西方（WEIRD）群体的研究仍面临巨大挑战。本文提出一种新方法：利用大语言模型（LLMs）创建代表这些群体的合成文化代理人（SCAs），并将其用于经典行为实验，如独裁者博弈和最后通牒博弈。结果表明，不同文化间存在显著行为差异。对于已有数据的群体，SCAs的行为与真实人类被试表现出一致的定性特征；对于未研究过的群体，该方法可生成新的、可检验的假设。通过将AI融入实验经济学，该方法为难以接触的人群提供了有效且伦理上可行的实验预研手段。本研究为跨文化经济研究提供新工具，展示了大模型在行为实验中的潜力。
原文摘要 · Abstract (English)
Despite its importance, studying economic behavior across diverse, non-WEIRD (Western, Educated, Industrialized, Rich, and Democratic) populations presents significant challenges. We address this issue by introducing a novel methodology that uses Large Language Models (LLMs) to create synthetic cultural agents (SCAs) representing these populations. We subject these SCAs to classic behavioral experiments, including the dictator and ultimatum games. Our results demonstrate substantial cross-cultural variability in experimental behavior. Notably, for populations with available data, SCAs' behaviors qualitatively resemble those of real human subjects. For unstudied populations, our method can generate novel, testable hypotheses about economic behavior. By integrating AI into experimental economics, this approach offers an effective and ethical method to pilot experiments and refine protocols for hard-to-reach populations. Our study provides a new tool for cross-cultural economic studies and demonstrates how LLMs can help experimental behavioral research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。