教开发者如何让机器学习更可信，不只是准确。
Engineering Trustworthy AI: A Developer Guide for Empirical Risk Minimization
- 把可信性要求转化为模型训练的具体设计
- 提升模型公平性与可解释性，减少偏差
- 适合关注AI伦理与工程落地的开发者
人工智能系统在个人与社会关键决策中日益发挥重要作用。尽管经验风险最小化（ERM）推动了多数AI成果，但其通常优先追求准确性，忽视可信性，常导致偏见、不透明等负面影响。本文探讨如何将可信AI的关键要求转化为ERM各组件的设计选择，旨在为构建符合新兴可信标准的AI系统提供可操作的指导。
原文摘要 · Abstract (English)
AI systems increasingly shape critical decisions across personal and societal domains. While empirical risk minimization (ERM) drives much of the AI success, it typically prioritizes accuracy over trustworthiness, often resulting in biases, opacity, and other adverse effects. This paper discusses how key requirements for trustworthy AI can be translated into design choices for the components of ERM. We hope to provide actionable guidance for building AI systems that meet emerging standards for trustworthiness of AI.
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。