把努力程度纳入算法公平性评估，更贴近人类对公平的直觉。
Effort-aware Fairness: Incorporating a Philosophy-informed, Human-centered Notion of Effort into Algorithmic Fairness Metrics
- 基于哲学中的‘力’概念，将特征随时间变化轨迹作为努力衡量标准。
- 实验显示人们更关注特征演变过程而非静态数值。
- 适用于司法与金融场景，帮助识别系统性劣势群体的不公平待遇。
尽管主流的AI公平性度量（如人口统计均等）揭示了辅助决策中的偏见，但未考虑个体在输入特征空间中所付出的努力。然而，努力的概念在哲学与人类对公平的理解中至关重要。本文提出一种哲学启发的效率感知公平性（EaF）方法，基于‘力’（Force）概念——即预测特征的时间轨迹与惯性相结合。理论构建之外，还包含：（1）一项注册制的人类受试者实验，结果显示在个人公平性评估的两个阶段中，人们更重视特征的时间演变路径而非其整体值；（2）在刑事司法与个人金融领域的效率感知个体/群体公平性计算流程。该研究可帮助AI审计人员发现并纠正那些虽付出巨大努力却仍受制于系统性劣势的个体所遭遇的不公平决策。
原文摘要 · Abstract (English)
Although popularized AI fairness metrics, e.g., demographic parity, have uncovered bias in AI-assisted decision-making outcomes, they do not consider how much effort one has spent to get to where one is today in the input feature space. However, the notion of effort is important in how Philosophy and humans understand fairness. We propose a philosophy-informed approach to conceptualize and evaluate Effort-aware Fairness (EaF), grounded in the concept of Force, which represents the temporal trajectory of predictive features coupled with inertia. Besides theoretical formulation, our empirical contributions include: (1) a pre-registered human subjects experiment, which shows that for both stages of the (individual) fairness evaluation process, people consider the temporal trajectory of a predictive feature more than its aggregate value; (2) pipelines to compute Effort-aware Individual/Group Fairness in the criminal justice and personal finance contexts. Our work may enable AI model auditors to uncover and potentially correct unfair decisions against individuals who have spent significant efforts to improve but are still stuck with systemic disadvantages outside their control.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。