Many high-stakes AI deployments proceed only if every stakeholder deems the system acceptable relative to their own minimum standard. With randomization over a finite menu of options, this becomes a feasibility question: does there exist a lottery over options that clears all stakeholders' acceptability bars? We study a query model where the algorithm proposes lotteries and receives only binary accept/reject feedback. We give deterministic and randomized algorithms that either find a unanimously acceptable lottery or certify infeasibility; adaptivity can avoid eliciting many stakeholders' constraints, and randomization further reduces the expected elicitation cost relative to full elicitation. We complement these upper bounds with worst-case lower bounds (in particular, linear dependence on the number of stakeholders and logarithmic dependence on precision are unavoidable). Finally, we develop learning-augmented algorithms that exploit natural forms of advice (e.g., likely binding stakeholders or a promising lottery), improving query complexity when predictions are accurate while preserving worst-case guarantees.

翻译：许多高风险AI系统的部署，只有在所有利益相关者根据其自身最低标准认为该系统可接受时才会进行。当对有限选项集进行随机化时，这便成为一个可行性问题：是否存在一个关于选项的抽彩方案，能够满足所有利益相关者的可接受性要求？我们研究了一种查询模型，其中算法提出抽彩方案，并仅接收二元接受/拒绝反馈。我们给出了确定性和随机化算法，这些算法要么找到一致可接受的抽彩方案，要么证明其不可行；自适应性可以避免引出许多利益相关者的约束条件，而随机化进一步降低了相对于完全引出的预期引出成本。我们用最坏情况下的下界（特别是，对利益相关者数量的线性依赖和对精度的对数依赖是不可避免的）来补充这些上界。最后，我们开发了学习增强型算法，该算法利用自然形式的建议（例如，可能的约束性利益相关者或一个有前景的抽彩方案），在保持最坏情况保证的同时，提高了预测准确时的查询复杂度。