Computational models are increasingly embedded in human-centered domains such as healthcare, education, workplace analytics, and digital well-being, where their predictions directly influence individual outcomes and collective welfare. In such contexts, achieving high accuracy alone is insufficient; models must also act ethically and equitably across diverse populations. However, fair AI approaches that rely on demographic attributes are impractical, as such information is often unavailable, privacy-sensitive, or restricted by regulatory frameworks. Moreover, conventional parity-based fairness approaches, while aiming for equity, can inadvertently violate core ethical principles by trading off subgroup performance or stability. To address this challenge, we present Flare (Fisher-guided LAtent-subgroup learning with do-no-harm REgularization), the first demographic-agnostic framework that aligns algorithmic fairness with ethical principles through the geometry of optimization. Flare leverages Fisher Information to regularize curvature, uncovering latent disparities in model behavior without access to demographic or sensitive attributes. By integrating representation, loss, and curvature signals, it identifies hidden performance strata and adaptively refines them through collaborative but do-no-harm optimization, enhancing each subgroup's performance while preserving global stability and ethical balance. We also introduce BHE (Beneficence-Harm Avoidance-Equity), a novel metric suite that operationalizes ethical fairness evaluation beyond statistical parity. Extensive evaluations across diverse physiological (EDA), behavioral (IHS), and clinical (OhioT1DM) datasets show that Flare consistently enhances ethical fairness compared to state-of-the-art baselines.

翻译：计算模型日益嵌入医疗、教育、工作场所分析和数字福祉等人类中心领域，其预测直接影响个体结果与集体福祉。在此类情境下，仅实现高精度不足；模型还需在不同人群中公平且合乎伦理地运作。然而，依赖人口统计属性的公平AI方法在实际中不可行，因该类信息通常不可获取、涉及隐私敏感或受监管框架限制。此外，传统基于均等性的公平方法虽以公平为目标，却可能因牺牲子群性能或稳定性而无意间违背核心伦理原则。为应对此挑战，我们提出Flare（费舍尔引导的潜在子群学习与"无伤害"正则化），这是首个通过优化几何将算法公平与伦理原则对齐的、无需人口统计信息的框架。Flare利用费舍尔信息正则化曲率，无需人口统计或敏感属性即可揭示模型行为的潜在差异。通过整合表征、损失和曲率信号，它识别隐藏的性能分层，并通过协作式"无伤害"优化自适应改进各层，在提升各子群性能的同时保持全局稳定性与伦理平衡。我们还提出BHE（益善性-伤害规避-公平性），这套超越统计均等性的新型度量指标将伦理公平评估付诸实践。在多样化生理（EDA）、行为（IHS）及临床（OhioT1DM）数据集上的广泛评估表明，相较于最先进的基线方法，Flare持续提升了伦理公平性。