对比7大AI模型与全球53国人类的金融决策，发现AI风险中性但有时不理性。
Artificial Finance: How AI Thinks About Money
- 用彩票题测试AI与人类决策，发现AI倾向追求期望值
- 面对现在与未来权衡时，部分AI回答违背理性原则
- AI整体反应最像坦桑尼亚人，暗示训练数据文化影响
本文系统比较了七种主流大语言模型（包括GPT-4o、GPT-4.5、o1、o3-mini、Gemini 2.0 Flash和DeepSeek R1）在金融决策问题上的回应，与来自53个国家的人类参与者数据进行对比。研究发现：第一，大语言模型在面对彩票类问题时普遍表现出风险中性特征，倾向于选择期望值最高的选项；第二，在权衡当下与未来收益时，部分模型出现与规范推理不符的不一致表现；第三，跨国家比较显示，模型的总体响应模式最接近坦桑尼亚参与者的答案。这些结果揭示了大语言模型在模拟人类决策行为中的机制，并凸显其输出中潜在的文化与训练数据影响。
原文摘要 · Abstract (English)
In this paper, we explore how large language models (LLMs) approach financial decision-making by systematically comparing their responses to those of human participants across the globe. We posed a set of commonly used financial decision-making questions to seven leading LLMs, including five models from the GPT series(GPT-4o, GPT-4.5, o1, o3-mini), Gemini 2.0 Flash, and DeepSeek R1. We then compared their outputs to human responses drawn from a dataset covering 53 nations. Our analysis reveals three main results. First, LLMs generally exhibit a risk-neutral decision-making pattern, favoring choices aligned with expected value calculations when faced with lottery-type questions. Second, when evaluating trade-offs between present and future, LLMs occasionally produce responses that appear inconsistent with normative reasoning. Third, when we examine cross-national similarities, we find that the LLMs' aggregate responses most closely resemble those of participants from Tanzania. These findings contribute to the understanding of how LLMs emulate human-like decision behaviors and highlight potential cultural and training influences embedded within their outputs.
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。