从效率到公平：衡量偏好学习中的公平性
From Efficiency to Equity: Measuring Fairness in Preference Learning
AI总结：
本文借鉴不平等与罗尔斯正义理论，提出基于 Gini Coefficient、Atkinson Index 和 Kuznets Ratio 的偏好学习认知公平评估框架，并通过两个数据集验证及缓解策略分析效率与公平的权衡。
摘要：
随着人工智能系统（尤其是生成模型）日益影响决策，确保它们能够公平代表多样化的人类偏好变得至关重要。本文受不平等经济学理论和罗尔斯正义论启发，提出了一个用于评估偏好学习模型认知公平性的新颖框架。我们提出改编自 Gini Coefficient、Atkinson Index 和 Kuznets Ratio 的指标，以量化这些模型中的公平性。我们使用两个数据集验证该方法：一个定制的视觉偏好数据集（AI-EDI-Space）和 Jester Jokes 数据集。分析揭示了模型性能在不同用户之间的差异，凸显了潜在的认知不公。我们探索了预处理和处理中技术以缓解这些不平等，结果表明模型效率与公平性之间存在复杂关系。本工作为人工智能伦理作出贡献，提供了一个评估并改进偏好学习模型认知公平性的框架，也为在多样化人类偏好至关重要的场景中开发更具包容性的人工智能系统提供了洞见。
英文摘要：
As AI systems, particularly generative models, increasingly influence decision-making, ensuring that they are able to fairly represent diverse human preferences becomes crucial. This paper introduces a novel framework for evaluating epistemic fairness in preference learning models inspired by economic theories of inequality and Rawlsian justice. We propose metrics adapted from the Gini Coefficient, Atkinson Index, and Kuznets Ratio to quantify fairness in these models. We validate our approach using two datasets: a custom visual preference dataset (AI-EDI-Space) and the Jester Jokes dataset. Our analysis reveals variations in model performance across users, highlighting potential epistemic injustices. We explore pre-processing and in-processing techniques to mitigate these inequalities, demonstrating a complex relationship between model efficiency and fairness. This work contributes to AI ethics by providing a framework for evaluating and improving epistemic fairness in preference learning models, offering insights for developing more inclusive AI systems in contexts where diverse human preferences are crucial.
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。
