Built independently by an author, for readers. Read the story and support ChapterPal

keyword

contrastive explanations

Contrastive explanations are explanations that address why a specific event or decision occurred instead of a particular alternative outcome, rather than attempting to describe the entire causal history of the event. Formulated to answer the question of why one outcome happened rather than another, they operate by comparing the observed outcome, known as the fact, against a non-occurring reference outcome, known as the foil. By focusing exclusively on the distinguishing features, causes, or conditions that differentiate the fact from the foil, contrastive explanations provide concise, contextually relevant justifications that align closely with human cognitive reasoning and facilitate the interpretability of complex systems.

1 item

Explanation in Artificial Intelligence: Insights from the Social Sciences

Explanation in Artificial Intelligence: Insights from the Social Sciences

Tim Miller

OrganizationsUniversity of Melbourne

Why you should read this

Synthesizes decades of findings from philosophy, cognitive science, and social psychology to define how explainable artificial intelligence should align with human cognitive biases and social expectations rather than developer intuition.

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.

Added

2026-09-12