无同侪的相互评估与监督
Mutual Evaluation and Supervision without Peers
- Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种无需同侪的相互评估与监督机制，通过批评者规则和条件独立复制实现真实报告激励，产生无偏信息分数，并分析策略性影响。
AI中文摘要：
本文介绍了一种可复制任务工作者与批评者之间的相互评估机制，该机制激励真实报告，两者均被建模为策略性智能体。批评者选择一个有限值规则，该规则在联合报告分布上诱导出一个评估分数。他们的共同收益通过相对于无限制批评者包络的遗憾值进行分析。批评者规则与评估分数是截然不同的。这一类别实现了一种无需同侪的信息抽取机制，利用同一任务上工作者的条件独立复制。该复制循环机制通过同任务复制和新任务样本实现类型一致收益。与同侪预测和评分规则文献相比，本文展示了能够产生无偏的皮尔逊和香农信息分数，且无需同侪、真实参考或似然比估计。一个有效的二元批评者也可以通过共享的工作者回报的有限类型注释来表示。一个运行时限制是所需复制数量是随机的，且可能依赖于批评者规则。其他时序效应，如承诺和重新优化，会产生不同的激励，将该框架与变分同侪预测联系起来。这一机制类别说明了为什么策略性考虑对批评者和工作者智能体都至关重要。
英文摘要：
This article introduces mutual evaluation of a replicable task worker and a critic that incentivizes truthful reporting, both modeled as strategic agents. The critic chooses a finite-valued rule that induces an evaluation score on joint report laws. Their common payoff is analyzed through regret relative to the unrestricted critic envelope. The critic rule is distinct from the evaluation score. This class enables a peer-free information elicitation mechanism using conditionally independent replications of a worker on the same task. This replication-loop mechanism implements a type-agreement payoff using same-task replications and new-task samples. In contrast to the peer-prediction and scoring-rule literature, implementations are shown that produce unbiased Pearson and Shannon information scores without requiring peers, a ground-truth reference, or likelihood-ratio estimation. A valid binary critic also can be represented by shared finite type annotations of worker returns. One runtime restriction is that the number of required replicas is random and can depend on the critic rule. Other timing effects, such as commitment and reoptimization, yield distinct incentives, connecting the framework to variational peer prediction. This mechanism class illustrates why strategic considerations matter for both critic and worker agents.
