DeepAI AI Chat
Log In Sign Up

Contrastive Explanation: A Structural-Model Approach

by   Tim Miller, et al.

The topic of causal explanation in artificial intelligence has gathered interest in recent years as researchers and practitioners aim to increase trust and understanding of intelligent decision-making and action. While different sub-fields have looked into this problem with a sub-field-specific view, there are few models that aim to capture explanation in AI more generally. One general model is based on structural causal models. It defines an explanation as a fact that, if found to be true, would constitute an actual cause of a specific event. However, research in philosophy and social sciences shows that explanations are contrastive: that is, when people ask for an explanation of an event -- the fact --- they (sometimes implicitly) are asking for an explanation relative to some contrast case; that is, "Why P rather than Q?". In this paper, we extend the structural causal model approach to define two complementary notions of contrastive explanation, and demonstrate them on two classical AI problems: classification and planning. We believe that this model can be used to define contrastive explanation of other subfield-specific AI models.


page 1

page 2

page 3

page 4


Causes and Explanations: A Structural-Model Approach. Part II: Explanations

We propose new definitions of (causal) explanation, using structural equ...

On the Injunction of XAIxArt

The position paper highlights the range of concerns that are engulfed in...

Causal Explanations and XAI

Although standard Machine Learning models are optimized for making predi...

Structure-Based Causes and Explanations in the Independent Choice Logic

This paper is directed towards combining Pearl's structural-model approa...

Evaluating computational models of explanation using human judgments

We evaluate four computational models of explanation in Bayesian network...

Tradeoff-Focused Contrastive Explanation for MDP Planning

End-users' trust in automated agents is important as automated decision-...

Behaviour Trees for Conversational Explanation Experiences

Explainable AI (XAI) has the potential to make a significant impact on b...