DeepAI AI Chat
Log In Sign Up

Contrastive Explanation: A Structural-Model Approach

11/07/2018
by   Tim Miller, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/20/2002

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

We propose new definitions of (causal) explanation, using structural equ...
09/12/2023

On the Injunction of XAIxArt

The position paper highlights the range of concerns that are engulfed in...
01/31/2022

Causal Explanations and XAI

Although standard Machine Learning models are optimized for making predi...
10/19/2012

Structure-Based Causes and Explanations in the Independent Choice Logic

This paper is directed towards combining Pearl's structural-model approa...
09/26/2013

Evaluating computational models of explanation using human judgments

We evaluate four computational models of explanation in Bayesian network...
04/27/2020

Tradeoff-Focused Contrastive Explanation for MDP Planning

End-users' trust in automated agents is important as automated decision-...
11/11/2022

Behaviour Trees for Conversational Explanation Experiences

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