Niloy Ganguly, Dren Fazlija, Maryam Badar, Marco Fisichella, Sandipan Sikdar...
TL;DR本文综述了因果方法对于提高可信 AI 解决方案的应用和发展，因为现有的 AI 模型大多缺乏对人类真实世界理解的因果关系的认识，从而导致了模型泛化性能差、不公平以及难以解释等问题。
Abstract
State-of-the-art ai models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not generalize to unseen data, often pro