Proponents of explainable AI have often argued that it constitutes an essential path towards algorithmic fairness. Prior works examining these claims have primarily evaluated explanations based on their effects on humans' perceptions, but there is scant research on the relationship between explanations and distributive fairness of AI-assisted decisions. In this paper, we conduct an empirical study to examine the relationship between feature-based explanations and distributive fairness, mediated by human perceptions and reliance on AI recommendations. Our findings show that explanations influence fairness perceptions, which, in turn, relate to humans' tendency to adhere to AI recommendations. However, our findings suggest that such explanations do not enable humans to discern correct and wrong AI recommendations. Instead, we show that they may affect reliance irrespective of the correctness of AI recommendations. Depending on which features an explanation highlights, this can foster or hinder distributive fairness: when explanations highlight features that are task-irrelevant and evidently associated with the sensitive attribute, this prompts overrides that counter stereotype-aligned AI recommendations. Meanwhile, if explanations appear task-relevant, this induces reliance behavior that reinforces stereotype-aligned errors. These results show that feature-based explanations are not a reliable mechanism to improve distributive fairness, as their ability to do so relies on a human-in-the-loop operationalization of the flawed notion of "fairness through unawareness". Finally, our study design provides a blueprint to evaluate the suitability of other explanations as pathways towards improved distributive fairness of AI-assisted decisions.

翻译：可解释人工智能的支持者常主张，解释是实现算法公平的重要途径。先前对这类主张的检验主要基于解释对人类感知的影响，但关于解释与AI辅助决策中分配公平之间关系的研究甚少。本文通过实证研究，探讨基于特征的解释与分配公平之间的关系，并考察人类感知及对AI建议的依赖在这种关系中的中介作用。研究结果表明，解释会影响公平感知，而公平感知又与人类遵从AI建议的倾向相关。然而，本研究的发现表明，这类解释并未使人类能够区分AI建议的正确与错误。相反，我们证明解释可能独立于AI建议的正确性而影响依赖行为。根据解释所强调的特征不同，这可能促进或阻碍分配公平：当解释强调与任务无关且明显与敏感属性相关的特征时，会引发推翻符合刻板印象的AI建议的过度纠正行为；而若解释看似与任务相关，则会导致强化刻板印象错误的依赖行为。这些结果表明，基于特征的解释并非提高分配公平的可靠机制——因为其实现公平的能力依赖于将"通过无意识实现公平"这一有缺陷概念以人机协作方式操作化。此外，本研究设计为评估其他解释作为提升AI辅助决策分配公平的路径提供了蓝图。