AI 中文总结
该研究通过让代表性样本向GPT-5.2撰写理财提示词，模拟发现遵循其建议可使受访者符合生命周期理财理论，且理财建议的性别差异源于需求和供给端因素。
AI 中文摘要
我们邀请代表性样本撰写向大型语言模型（LLMs）寻求支出与投资建议的提示词，随后在现实资产与劳动力市场条件下模拟遵循该建议的终身影响。将此方法应用于GPT-5.2，我们发现遵循其建议会使受访者向生命周期理论靠拢：更多人参与多元化股票基金、股票占比随年龄下降、储蓄缓冲更大。建议因性别、过往AI经验和金融知识水平呈现系统性差异；就性别而言，三分之二的股票占比差异源于男女撰写的提示词不同（需求端），三分之一源于相同提示词附加的性别标签（供给端）。
英文摘要
We ask a representative sample to write prompts seeking spending and investing advice from LLMs, then simulate the lifetime effects of following the advice under realistic asset and labor market conditions. Applying this method to GPT-5.2, we find following the advice would move respondents toward life cycle theory: broader participation in diversified equity funds, age-declining equity shares, and larger savings buffers. Recommendations vary systematically by gender, prior AI experience, and financial literacy. For gender, two-thirds of recommended equity-share differences arise from men and women writing different prompts (demand), while one-third arise from gender labels attached to otherwise identical prompts (supply).
Comments92 pages, 38 figures, 10 tables
