Explanation in artificial intelligence: Insights from the social sciences
Explanation in artificial intelligence: Insights from the social sciences
复制标题
DOI：
10.1016/j.artint.2018.07.007
复制
发表时间：
2019-02-01
影响因子：
14.4
通讯作者：
Miller, Tim
中科院分区：
文献类型：
--
作者：
Miller, Tim
最近，可解释人工智能领域出现了复苏，因为研究人员和从业者试图为他们的算法提供更多的透明度。这些研究的大部分都集中在向人类观察者明确解释决策或行动上，并且不应该有争议地说，研究人类如何相互解释可以作为人工智能解释的有用起点。然而，公平地说，大多数可解释人工智能的工作只使用研究人员对什么构成“好”解释的直觉。在哲学、心理学和认知科学中，存在着大量有价值的研究，研究人们如何定义、生成、选择、评估和呈现解释，这些研究认为人们在解释过程中会使用某些认知偏见和社会期望。本文认为，可解释的人工智能领域可以建立在现有的研究，并回顾了哲学，认知心理学/科学和社会心理学，研究这些主题的相关论文。它引出了一些重要的发现，并讨论了如何将这些发现与可解释的人工智能工作结合起来。(C)2018爱思唯尔B. V.保留所有权利。
There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to provide more transparency to their algorithms. Much of this research is focused on explicitly explaining decisions or actions to a human observer, and it should not be controversial to say that looking at how humans explain to each other can serve as a useful starting point for explanation in artificial intelligence. However, it is fair to say that most work in explainable artificial intelligence uses only the researchers' intuition of what constitutes a 'good' explanation. There exist vast and valuable bodies of research in philosophy, psychology, and cognitive science of how people define, generate, select, evaluate, and present explanations, which argues that people employ certain cognitive biases and social expectations to the explanation process. This paper argues that the field of explainable artificial intelligence can build on this existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics. It draws out some important findings, and discusses ways that these can be infused with work on explainable artificial intelligence. (C) 2018 Elsevier B.V. All rights reserved.