arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.22236cs.GTcs.HCcs.LGecon.EM
收藏

算法特征突出用于人机决策制定

Algorithmic Feature Highlighting for Human-AI Decision-Making

Stanford University(斯坦福大学)

Yifan Guo, Jann Spiess

AI总结:

本文研究了在复杂情况下通过突出少量特定特征来辅助人类决策的算法,探讨了不同人类认知模式下特征选择的优化问题,并通过实证研究验证了该方法的实用性。

摘要:

人类决策者常面临复杂案例中众多潜在相关特征的选择难题,但信息处理能力有限。本文研究了在此类情境下突出少量特定特征供人类考虑的算法,而非直接给出预测或建议。将突出视为一种受约束的信息策略,选择少量特征揭示。核心问题在于人类如何解读算法的特征选择:精明的代理会根据选择规则进行条件概率更新,而粗心的代理仅根据揭示的特征值更新,并将选择事件视为外生因素。我们证明,为精明代理优化突出在简单离散和二元设置中可能计算上不可行,而为粗心代理优化只要最大带宽固定则可行。此外,为精明代理最优的突出策略在部署到粗心代理时可能表现极差,这促使了鲁棒且可实施的替代方案。我们基于美国住房调查进行了校准的实证研究。总体而言,我们的结果证明了突出特定情境下的特征集而非固定集作为实现人机互补的实用且计算可行的工具的价值。

英文摘要:

Human decision-makers often face choices about complex cases with many potentially relevant features, but limited bandwidth to inspect and integrate all available information. In such settings, we study algorithms that highlight a small subset of case-specific features for human consideration, rather than producing a single prediction or recommendation. We model highlighting as a constrained information policy that selects a small number of features to reveal. A central issue is how humans interpret the algorithm's choice of features: a sophisticated agent correctly conditions on the selection rule, while a naive agent updates only on revealed feature values and treats the selection event as exogenous. We show that optimizing highlighting for sophisticated agents can be computationally intractable, even in simple discrete and binary settings, whereas optimizing for naive agents is tractable as long as the maximal bandwidth is fixed. We also show that a highlighting policy that is optimal for sophisticated agents can perform arbitrarily poorly when deployed to naive agents, motivating robust, implementable alternatives. We illustrate our framework in a calibrated empirical exercise based on the American Housing Survey. Overall, our results establish the value of highlighting a context-specific set of features rather than a fixed one as a practically appealing and computationally feasible tool for achieving human-algorithm complementarity.

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。

↑