DeepAI AI Chat
Log In Sign Up

Causal Explanations and XAI

by   Sander Beckers, et al.

Although standard Machine Learning models are optimized for making predictions about observations, more and more they are used for making predictions about the results of actions. An important goal of Explainable Artificial Intelligence (XAI) is to compensate for this mismatch by offering explanations about the predictions of an ML-model which ensure that they are reliably action-guiding. As action-guiding explanations are causal explanations, the literature on this topic is starting to embrace insights from the literature on causal models. Here I take a step further down this path by formally defining the causal notions of sufficient explanations and counterfactual explanations. I show how these notions relate to (and improve upon) existing work, and motivate their adequacy by illustrating how different explanations are action-guiding under different circumstances. Moreover, this work is the first to offer a formal definition of actual causation that is founded entirely in action-guiding explanations. Although the definitions are motivated by a focus on XAI, the analysis of causal explanation and actual causation applies in general. I also touch upon the significance of this work for fairness in AI by showing how actual causation can be used to improve the idea of path-specific counterfactual fairness.


page 1

page 2

page 3

page 4


The privacy issue of counterfactual explanations: explanation linkage attacks

Black-box machine learning models are being used in more and more high-s...

Causal Dependence Plots for Interpretable Machine Learning

Explaining artificial intelligence or machine learning models is an incr...

Contrastive Explanation: A Structural-Model Approach

The topic of causal explanation in artificial intelligence has gathered ...

Interpretable Data-Based Explanations for Fairness Debugging

A wide variety of fairness metrics and eXplainable Artificial Intelligen...

A Causal Perspective on Meaningful and Robust Algorithmic Recourse

Algorithmic recourse explanations inform stakeholders on how to act to r...

Why Don't You Do Something About It? Outlining Connections between AI Explanations and User Actions

A core assumption of explainable AI systems is that explanations change ...