专业AI决策更易偏差，通用模型反而更理性。
Economic Rationality under Specialization: Evidence of Decision Bias in AI Agents
- 对比专业与通用AI在经济决策中的表现
- 专业模型越深入，越违背理性原则（GARP违反率上升）
- 适合设计需稳定理性的AI系统时参考
Chen等（2023）[01]发现，大语言模型GPT在预算分配和风险偏好等任务中表现出与普通人相当或更高的经济理性。本文在此基础上引入生物技术专家、经济学家等专业化代理，横向比较其在类似决策场景中的表现，探究专业化是否能提升或维持与GPT相当的经济理性。结果显示，当代理在特定领域投入更多精力时，其决策行为更易出现‘理性漂移’，具体表现为：违反广义揭示偏好公理（GARP）的比例上升、临界成本效率指数（CCEI）下降，以及在高风险条件下决策偏差更大。相比之下，GPT及更通用的基础代理在多项任务中保持了更稳定、一致的理性水平。该研究揭示了专业化与经济理性之间的内在矛盾，为构建兼顾专业化与通用性的AI决策系统提供了新视角。
原文摘要 · Abstract (English)
In the study by Chen et al. (2023) [01], the large language model GPT demonstrated economic rationality comparable to or exceeding the average human level in tasks such as budget allocation and risk preference. Building on this finding, this paper further incorporates specialized agents, such as biotechnology experts and economists, for a horizontal comparison to explore whether specialization can enhance or maintain economic rationality equivalent to that of GPT in similar decision-making scenarios. The results indicate that when agents invest more effort in specialized fields, their decision-making behavior is more prone to 'rationality shift,' specifically manifested as increased violations of GARP (Generalized Axiom of Revealed Preference), decreased CCEI (Critical Cost Efficiency Index), and more significant decision deviations under high-risk conditions. In contrast, GPT and more generalized basic agents maintain a more stable and consistent level of rationality across multiple tasks. This study reveals the inherent conflict between specialization and economic rationality, providing new insights for constructing AI decision-making systems that balance specialization and generalization across various scenarios.
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。