可接受性对齐
Admissibility Alignment
AI总结：
本文提出MAP-AI架构，通过蒙特卡洛方法评估决策策略的可接受性，实现AI对齐的动态决策理论属性。
摘要：
本文介绍了可接受性对齐：将AI对齐重新定义为在不确定性下对结果分布上的可接受行动和决策选择的属性，通过候选策略的行为来评估。我们提出了MAP-AI（蒙特卡洛对齐用于策略）作为实现可接受性对齐的典型系统架构，将对齐正式化为概率性的决策理论属性，而不是静态或二元条件。MAP-AI是一种新的控制平面系统架构，用于在不确定性下实现对齐的决策，通过蒙特卡洛估计结果分布和受可接受性控制的策略选择来实现对齐，而不是静态的模型级约束。该框架在可能的未来集合上评估决策策略，明确建模不确定性、干预效应、价值模糊性和治理约束。对齐通过分布属性如期望效用、方差、尾部风险和误对齐概率来评估，而不是准确度或排名性能。这种方法区分了概率预测与在不确定性下的决策推理，并提供了一种可执行的方法来评估企业和服务机构AI系统中的信任和对齐。结果是一种实用的基础，用于管理其影响由个体预测决定，而不是由策略行为在分布和尾部事件上的行为决定的AI系统。最后，我们展示了如何将分布对齐评估整合到决策本身中，从而产生一个受可接受性控制的行动选择机制，在不确定性下改变策略行为，而无需重新训练或修改底层模型。
英文摘要：
This paper introduces Admissibility Alignment: a reframing of AI alignment as a property of admissible action and decision selection over distributions of outcomes under uncertainty, evaluated through the behavior of candidate policies. We present MAP-AI (Monte Carlo Alignment for Policy) as a canonical system architecture for operationalizing admissibility alignment, formalizing alignment as a probabilistic, decision-theoretic property rather than a static or binary condition. MAP-AI, a new control-plane system architecture for aligned decision-making under uncertainty, enforces alignment through Monte Carlo estimation of outcome distributions and admissibility-controlled policy selection rather than static model-level constraints. The framework evaluates decision policies across ensembles of plausible futures, explicitly modeling uncertainty, intervention effects, value ambiguity, and governance constraints. Alignment is assessed through distributional properties including expected utility, variance, tail risk, and probability of misalignment rather than accuracy or ranking performance. This approach distinguishes probabilistic prediction from decision reasoning under uncertainty and provides an executable methodology for evaluating trust and alignment in enterprise and institutional AI systems. The result is a practical foundation for governing AI systems whose impact is determined not by individual forecasts, but by policy behavior across distributions and tail events. Finally, we show how distributional alignment evaluation can be integrated into decision-making itself, yielding an admissibility-controlled action selection mechanism that alters policy behavior under uncertainty without retraining or modifying underlying models.
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。
