BriefGPT.xyz
Dec, 2022
人工智能系统中的排外表现
Manifestations of Xenophobia in AI Systems
HTML
PDF
Nenad Tomasev, Jonathan Leader Maynard, Iason Gabriel
TL;DR
本论文旨在填补现有机器学习公平框架未全面测量或减轻由于排外主义导致的伤害的概念差距，并通过分析排外主义对社交媒体和推荐系统、医疗保健、移民、就业以及大型预先训练模型的潜在影响，推动未来人工智能系统的包容性设计。
Abstract
xenophobia
is one of the key drivers of marginalisation, discrimination, and conflict, yet many prominent
machine learning
(ML)
fairness framewor
→