重新定义AI偏见：有偏模型也可能公平，关键在区分偏见与歧视
Defining bias in AI-systems: Biased models are fair models
- 将偏见与歧视分离，提出偏见不等于不公平的新视角
- 挑战'无偏即公平'的常识，强调概念清晰的重要性
- 适合关注算法公平性理论基础的研究者阅读
关于AI系统中偏见的讨论是算法公平性议题的核心。然而，尽管频繁与公平性相对比，'偏见'一词往往缺乏明确定义，暗示无偏模型即为公平模型。本文质疑这一假设，认为要有效应对公平问题，必须对偏见进行精确的概念界定。我们指出，不应将偏见视为固有的负面或不公平因素，而应重视偏见与歧视之间的区别。这一视角转变有助于在学术界关于AI公平性的讨论中建立更建设性的对话。
原文摘要 · Abstract (English)
The debate around bias in AI systems is central to discussions on algorithmic fairness. However, the term bias often lacks a clear definition, despite frequently being contrasted with fairness, implying that an unbiased model is inherently fair. In this paper, we challenge this assumption and argue that a precise conceptualization of bias is necessary to effectively address fairness concerns. Rather than viewing bias as inherently negative or unfair, we highlight the importance of distinguishing between bias and discrimination. We further explore how this shift in focus can foster a more constructive discourse within academic debates on fairness in AI systems.
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。