将AI偏见视为对称性破坏，帮开发者判断该保留还是消除。
AI Biases as Asymmetries: A Review to Guide Practice
- 把偏见看作对称性标准的违反，重新定义其本质。
- 区分误差、不平等和过程三类偏见，识别其好坏与不可避免场景。
- 适合研究伦理、系统设计与政策制定者参考。
当前对人工智能中偏见的理解正经历变革。以往将其视为错误或缺陷，如今越来越多地认识到偏见是系统固有属性，有时甚至优于无偏替代方案。本文回顾这一转变的原因，并就两个核心问题提供新指导：第一，如何基于新理解来思考与度量AI系统中的偏见？第二，哪些偏见应接受甚至放大，哪些应最小化或消除，原因何在？我们主张，关键在于将偏见理解为‘对称性标准的违背’（遵循Kelly）。本文区分三类主要不对称性：误差偏见、不平等偏见和过程偏见，并指出在AI开发与应用流程中，每种偏见可能有益、有害或不可避免的具体环节。
原文摘要 · Abstract (English)
The understanding of bias in AI is currently undergoing a revolution. Initially understood as errors or flaws, biases are increasingly recognized as integral to AI systems and sometimes preferable to less biased alternatives. In this paper, we review the reasons for this changed understanding and provide new guidance on two questions: First, how should we think about and measure biases in AI systems, consistent with the new understanding? Second, what kinds of bias in an AI system should we accept or even amplify, and what kinds should we minimize or eliminate, and why? The key to answering both questions, we argue, is to understand biases as "violations of a symmetry standard" (following Kelly). We distinguish three main types of asymmetry in AI systems-error biases, inequality biases, and process biases-and highlight places in the pipeline of AI development and application where bias of each type is likely to be good, bad, or inevitable.
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。