Explanation in Artificial Intelligence: Insights from the Social Sciences
Tim Miller School of Computing and Information Systems University of Melbourne, Melbourne, Australia
Abstract
There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to make their algorithms more understandable. 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 exists 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 towards the explanation process. This paper argues that the field of explainable artificial intelligence should 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 b
中文速览
可解释人工智能（XAI）领域正在快速发展，但大多数研究者在设计"好的解释"时仅凭自身直觉，却忽视了哲学、心理学和认知科学中数十年积累的关于人类如何理解、生成和评价解释的丰富研究成果。这篇论文系统梳理了来自上述社会科学领域的250余篇文献，归纳出四条对AI解释设计至关重要的核心发现：解释是对比性的（人们问的不是"为什么是P"，而是"为什么是P而不是Q"）、解释是有偏向地被筛选的（人们只关注少数几个原因而非全部因果链）、概率统计本身说服力有限（没有因果支撑的统计关联难以令人信服）、解释本质上是社会性互动（解释者需要根据对听者认知状态的判断来调整内容）。研究者认为，如果忽视这些人类认知规律，仅从计算角度构建可解释AI系统，将难以真正赢得用户信任；将社会科学的解释理论纳入XAI的设计框架，才是构建真正有用的可解释智能系统的正确路径。
原文 arXiv:1706.07269;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1706.07269v3