The hidden assumptions behind counterfactual explanations and principal reasons
Counterfactual explanations are gaining prominence within technical, legal, and business
circles as a way to explain the decisions of a machine learning model. These explanations …
circles as a way to explain the decisions of a machine learning model. These explanations …
Counterfactual explanations can be manipulated
D Slack, A Hilgard, H Lakkaraju… - Advances in neural …, 2021 - proceedings.neurips.cc
Counterfactual explanations are emerging as an attractive option for providing recourse to
individuals adversely impacted by algorithmic decisions. As they are deployed in critical …
individuals adversely impacted by algorithmic decisions. As they are deployed in critical …
Achieving diversity in counterfactual explanations: a review and discussion
In the field of Explainable Artificial Intelligence (XAI), counterfactual examples explain to a
user the predictions of a trained decision model by indicating the modifications to be made …
user the predictions of a trained decision model by indicating the modifications to be made …
[PDF][PDF] Counterfactual explanations for machine learning: A review
S Verma, J Dickerson, K Hines - arXiv preprint arXiv …, 2020 - ml-retrospectives.github.io
Abstract Machine learning plays a role in many deployed decision systems, often in ways
that are difficult or impossible to understand by human stakeholders. Explaining, in a human …
that are difficult or impossible to understand by human stakeholders. Explaining, in a human …
Counterfactual explanations and algorithmic recourses for machine learning: A review
Machine learning plays a role in many deployed decision systems, often in ways that are
difficult or impossible to understand by human stakeholders. Explaining, in a human …
difficult or impossible to understand by human stakeholders. Explaining, in a human …
Robustness in machine learning explanations: does it matter?
L Hancox-Li - Proceedings of the 2020 conference on fairness …, 2020 - dl.acm.org
The explainable AI literature contains multiple notions of what an explanation is and what
desiderata explanations should satisfy. One implicit source of disagreement is how far the …
desiderata explanations should satisfy. One implicit source of disagreement is how far the …
FACE: feasible and actionable counterfactual explanations
Work in Counterfactual Explanations tends to focus on the principle of" the closest possible
world" that identifies small changes leading to the desired outcome. In this paper we argue …
world" that identifies small changes leading to the desired outcome. In this paper we argue …
Carla: a python library to benchmark algorithmic recourse and counterfactual explanation algorithms
M Pawelczyk, S Bielawski, J Heuvel, T Richter… - arXiv preprint arXiv …, 2021 - arxiv.org
Counterfactual explanations provide means for prescriptive model explanations by
suggesting actionable feature changes (eg, increase income) that allow individuals to …
suggesting actionable feature changes (eg, increase income) that allow individuals to …
Evaluating robustness of counterfactual explanations
Transparency is a fundamental requirement for decision making systems when these should
be deployed in the real world. It is usually achieved by providing explanations of the …
be deployed in the real world. It is usually achieved by providing explanations of the …
Explaining machine learning classifiers through diverse counterfactual explanations
Post-hoc explanations of machine learning models are crucial for people to understand and
act on algorithmic predictions. An intriguing class of explanations is through counterfactuals …
act on algorithmic predictions. An intriguing class of explanations is through counterfactuals …