Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
John J. Horton MIT、NBER Apostolos Filippas Fordham Benjamin S. Manning MIT
Abstract
We argue that newly-developed large language models (LLMs), because of how they are trained and designed, are implicit computational models of humans—a Homo silicus. LLMs can be used like economists use Homo economicus: they can be given endowments, information, preferences, and so on, and then their behavior can be explored in scenarios via simulation. Experiments using this approach, derived from Charness and Rabin (2002), Kahneman et al. (1986), Samuelson and Zeckhauser (1988), Oprea (2024b), and Horton (2025), show qualitatively similar results to the original, and when they differ, it is often generative for future research. We discuss potential applications, conceptual issues, and why this approach can inform the study of humans.
中文速览
大型语言模型（LLM）因其训练方式天然内化了大量人类行为模式，作者将其称为"硅基智人"（Homo silicus），并提出可以像经济学家使用"理性经济人"假设那样，把LLM当作人类行为的计算模型来做模拟实验。研究团队重现并扩展了五项经典经济学实验——涵盖价格哄抬的公平感知、社会偏好与分配决策、现状偏差、风险态度的复杂性解释，以及最低工资对雇主招聘行为的影响——结果发现LLM的模拟表现与人类被试高度吻合，偶尔出现的偏差反而启发了新的研究问题。这一方法的最大价值在于速度极快、成本极低，研究者可以在真正开展人类实验之前，用AI预先探索参数空间、检验问卷措辞的敏感性并指导样本量估算，从而大幅降低社会科学研究的试错成本。
原文 arXiv:2301.07543;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2301.07543v2