用人格模型测试AI投资行为，发现其能模拟人类三类心理特征。
Do LLM Personas Dream of Bull Markets? Comparing Human and AI Investment Strategies Through the Lens of the Five-Factor Model
- 给LLM赋予五大人格特质，模拟投资决策行为
- 在学习风格、冲动性、风险偏好上表现类人行为
- 仿真环境比问卷更真实反映AI类人行为
大型语言模型（LLMs）已展现出可模拟人格并表现出类人行为的能力。本研究探究具有特定大五人格特征的LLM人格是否能在投资任务中表现得与具有相同人格特质的人类一致。通过模拟投资任务，我们检验了这些结果能否推广至实际行为。结果显示，这些人格在所有评估维度均产生有意义的行为差异，且总体符合基于人类研究的预期。我们发现，LLM能将人格特质泛化为三类预期行为：学习风格、冲动性和风险偏好；而环境态度则无法准确体现。此外，我们表明，在仿真环境中，LLM的行为比在问卷环境中更贴近人类行为。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated the ability to adopt a personality and behave in a human-like manner. There is a large body of research that investigates the behavioural impacts of personality in less obvious areas such as investment attitudes or creative decision making. In this study, we investigated whether an LLM persona with a specific Big Five personality profile would perform an investment task similarly to a human with the same personality traits. We used a simulated investment task to determine if these results could be generalised into actual behaviours. In this simulated environment, our results show these personas produced meaningful behavioural differences in all assessed categories, with these behaviours generally being consistent with expectations derived from human research. We found that LLMs are able to generalise traits into expected behaviours in three areas: learning style, impulsivity and risk appetite while environmental attitudes could not be accurately represented. In addition, we showed that LLMs produce behaviour that is more reflective of human behaviour in a simulation environment compared to a survey environment.
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。