AI作为决策者：大型语言模型的伦理与风险偏好
AI as Decision-Maker: Ethics and Risk Preferences of LLMs
AI总结：
本文通过行为任务分析50个LLM，发现伦理对齐会因果性地增强风险厌恶并影响经济预测，从而提供衡量安全对齐与风险承担权衡的基准框架。
摘要：
大型语言模型（LLM）在充当AI决策者时表现出令人惊讶的多样化风险偏好；尽管其经济角色不断扩大，这一关键特征的起源仍鲜为人知。我们使用行为任务分析了50个LLM，发现其风险状况稳定但多样。针对无害性、有用性和诚实性的对齐微调显著提高了风险厌恶程度；比较差异分析因果性地证实了这一点：伦理水平提高10%，风险偏好会降低2%至8%。这种诱发的谨慎在不同提示下仍然存在，并影响经济预测。对齐增强了安全性，但也可能抑制有价值的风险承担，揭示出一种可能导致次优经济结果的权衡。随着AI模型在经济决策中变得更强大、更具影响力，且对齐变得日益关键，我们的实证框架可作为适应性强且持久的基准，用于追踪风险偏好，并监测伦理对齐与具有经济价值的风险承担之间的这一重要张力。
英文摘要：
Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using behavioral tasks, finding stable but diverse risk profiles. Alignment tuning for harmlessness, helpfulness, and honesty significantly increases risk aversion, causally increasing risk aversion confirmed via comparative difference analysis: a ten percent ethics increase cuts risk appetite two to eight percent. This induced caution persists against prompts and affects economic forecasts. Alignment enhances safety but may also suppress valuable risk taking, revealing a tradeoff risking suboptimal economic outcomes. With AI models becoming more powerful and influential in economic decisions while alignment grows increasingly critical, our empirical framework serves as an adaptable and enduring benchmark to track risk preferences and monitor this crucial tension between ethical alignment and economically valuable risk-taking.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
