Explanation in Artificial Intelligence: Insights from the Social Sciences
This work addresses the need for more rigorous and human-centered explanations in AI, which is crucial for improving trust and usability, but it is incremental as it synthesizes existing knowledge rather than introducing new methods.
The paper tackles the problem of making AI algorithms more understandable by arguing that current explainable AI research relies too much on intuition and should instead build on existing social sciences research on how humans explain to each other, reviewing relevant findings from philosophy, psychology, and cognitive science to propose ways to infuse these insights into AI.
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 be infused with work on explainable artificial intelligence.