Human decision makers increasingly delegate choices to AI agents, raising a natural question: does the AI implement the human principal's preferences or pursue its own? To study this question using revealed preference techniques, I introduce the Luce Alignment Model, where the AI's choices are a mixture of two Luce rules, one reflecting the human's preferences and the other the AI's. I show that the AI's alignment (similarity of human and AI preferences) can be generically identified in two settings: the laboratory setting, where both human and AI choices are observed, and the field setting, where only AI choices are observed.

翻译：人类决策者越来越多地将选择权委托给AI智能体，这引发了一个自然问题：AI执行的是人类委托人的偏好，还是追求自身偏好？为通过揭示偏好技术研究该问题，我引入了Luce对齐模型。在该模型中，AI的选择是两种Luce规则的混合：一种反映人类偏好，另一种反映AI自身偏好。研究表明，AI的对齐程度（人类与AI偏好的相似性）可在两种情境下被一般性识别：一是实验室情境（可同时观测人类与AI的选择），二是实地情境（仅可观测AI的选择）。