Economic choice prediction is an essential challenging task, often constrained by the difficulties in acquiring human choice data. Indeed, experimental economics studies had focused mostly on simple choice settings. The AI community has recently contributed to that effort in two ways: considering whether LLMs can substitute for humans in the above-mentioned simple choice prediction settings, and the study through ML lens of more elaborated but still rigorous experimental economics settings, employing incomplete information, repetitive play, and natural language communication, notably language-based persuasion games. This leaves us with a major inspiration: can LLMs be used to fully simulate the economic environment and generate data for efficient human choice prediction, substituting for the elaborated economic lab studies? We pioneer the study of this subject, demonstrating its feasibility. In particular, we show that a model trained solely on LLM-generated data can effectively predict human behavior in a language-based persuasion game, and can even outperform models trained on actual human data.

翻译：经济选择预测是一项重要的挑战性任务，通常受限于难以获取人类选择数据。事实上，实验经济学研究长期以来主要集中于简单的选择场景。近年来，人工智能领域通过两种方式为此做出贡献：一是探究大型语言模型能否在简单选择预测场景中替代人类，二是借助机器学习方法研究更为复杂但仍保持严谨性的实验经济学场景——这些场景涉及不完全信息、重复博弈以及自然语言交流（尤其是基于语言的游说博弈）。这给我们带来重要启示：能否利用大型语言模型完整模拟经济环境并生成数据，从而高效预测人类选择，进而取代复杂的经济学实验室研究？我们率先对此课题展开研究，验证了其可行性。具体而言，我们证明，仅基于大型语言模型生成数据训练的模型，能够有效预测基于语言的游说博弈中的人类行为，甚至其性能超越基于真实人类数据训练的模型。