简单创造不平等：公平、刻板印象和可解释性的含义
Simplicity Creates Inequity: Implications for Fairness, Stereotypes, and Interpretability
摘要：
算法越来越多地用于辅助或在某些情况下取代人类决策，特别是那些依赖于预测的决策。因此，除了预测质量之外，还有两个额外的功能引起了人们的兴趣：（i）为了促进人类与这些算法的交互和理解，我们希望预测函数在某种程度上是简单的或可解释的;（ii）因为它们会影响后续决策，我们也希望它们产生公平的分配。我们开发了一个正式的模型来探索简单性和公平性的需求之间的关系。虽然这两个概念似乎是由定性不同的目标的动机，我们显示了它们之间的根本不一致。具体来说，我们正式提出了一个一般框架，产生简单的预测功能，在这个框架中，我们建立了两个基本的结果。首先，每个简单的预测函数都是严格可改进的：存在一个更复杂的预测函数，它既严格更有效，也严格更公平。换句话说，使用简单的预测函数既降低了弱势群体的效用，也降低了相对于其他选项的整体福利。第二，我们表明，简单的预测功能必然会产生激励，以使用个人的信息在一个弱势群体的成员资格-激励，不存在之前的简化，并对这些人的工作。因此，简单化将劣势转化为对弱势群体的偏见。我们的研究结果不仅与算法有关，而且与任何产生简单模型的过程有关，因此它们与刻板印象的心理学和早期关于统计歧视的经济学文献有关。
英文摘要：
Algorithms are increasingly used to aid, or in some cases supplant, human decision-making, particularly for decisions that hinge on predictions. As a result, two additional features in addition to prediction quality have generated interest: (i) to facilitate human interaction and understanding with these algorithms, we desire prediction functions that are in some fashion simple or interpretable; and (ii) because they influence consequential decisions, we also want them to produce equitable allocations. We develop a formal model to explore the relationship between the demands of simplicity and equity. Although the two concepts appear to be motivated by qualitatively distinct goals, we show a fundamental inconsistency between them. Specifically, we formalize a general framework for producing simple prediction functions, and in this framework we establish two basic results. First, every simple prediction function is strictly improvable: there exists a more complex prediction function that is both strictly more efficient and also strictly more equitable. Put another way, using a simple prediction function both reduces utility for disadvantaged groups and reduces overall welfare relative to other options. Second, we show that simple prediction functions necessarily create incentives to use information about individuals' membership in a disadvantaged group --- incentives that weren't present before simplification, and that work against these individuals. Thus, simplicity transforms disadvantage into bias against the disadvantaged group. Our results are not only about algorithms but about any process that produces simple models, and as such they connect to the psychology of stereotypes and to an earlier economics literature on statistical discrimination.
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。
