用大模型模拟经济预期，让机器像人一样思考宏观经济。
Simulating Macroeconomic Expectations in Survey Experiments with LLM-based Economic Agents
- 构建带模块的大模型代理，能读取个人特征与外部信息。
- 生成的预期分布与人类数据高度相似，且符合人类思维模式。
- 适合研究行为经济学、政策模拟与AI认知差距的学者。
我们提出一种基于大语言模型经济代理（LLM Agents）的框架，用于在调查实验中模拟宏观经济预期。这些代理配备多个功能模块，可获取个人特征、先验预期及动态外部信息。通过复现三种典型调查设计，涵盖不同人群的多种预期，验证了该框架的有效性。结果表明，LLM Agents生成的预期分布与真实人类数据高度一致，并在开放式回答中捕捉到人类对齐的定性模式。评估显示，先验信息对匹配分布至关重要，而个人特征与外部信息则驱动类人思维过程。研究为缩小生成式AI与人类在宏观信念上的差距提供了方向，同时明确了该框架的适用边界。
原文摘要 · Abstract (English)
We introduce a framework for simulating macroeconomic expectations in survey experiments using LLM-based economic agents (LLM Agents). We construct LLM Agents equipped with several functional modules that retrieve personal characteristics, prior expectations, and dynamic external information. We validate our framework by recapitulating three representative survey designs covering various expectations across different types of respondents. Our results show that LLM Agents generate expectation distributions highly similar to human data and capture human-aligned qualitative patterns in open-ended responses. Evaluation reveals that priors are crucial for matching distributions, whereas personal and external information drive human-like thought processes. Our findings offer guidance for narrowing the belief gap between generative AI and humans at the aggregate level while delineating the boundaries of the framework.
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。