A survey of algorithmic recourse: contrastive explanations and consequential recommendations

AH Karimi, G Barthe, B Schölkopf, I Valera - ACM Computing Surveys, 2022‏ - dl.acm.org
Machine learning is increasingly used to inform decision making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …

Data-centric ai: Perspectives and challenges

D Zha, ZP Bhat, KH Lai, F Yang, X Hu - Proceedings of the 2023 SIAM …, 2023‏ - SIAM
The role of data in building AI systems has recently been significantly magnified by the
emerging concept of data-centric AI (DCAI), which advocates a fundamental shift from model …

[HTML][HTML] The perils and pitfalls of explainable AI: Strategies for explaining algorithmic decision-making

H de Bruijn, M Warnier, M Janssen - Government information quarterly, 2022‏ - Elsevier
Governments look at explainable artificial intelligence's (XAI) potential to tackle the criticisms
of the opaqueness of algorithmic decision-making with AI. Although XAI is appealing as a …

Problems with Shapley-value-based explanations as feature importance measures

IE Kumar, S Venkatasubramanian… - International …, 2020‏ - proceedings.mlr.press
Game-theoretic formulations of feature importance have become popular as a way to"
explain" machine learning models. These methods define a cooperative game between the …

Algorithmic recourse: from counterfactual explanations to interventions

AH Karimi, B Schölkopf, I Valera - … of the 2021 ACM conference on …, 2021‏ - dl.acm.org
As machine learning is increasingly used to inform consequential decision-making (eg, pre-
trial bail and loan approval), it becomes important to explain how the system arrived at its …

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 …

A survey of algorithmic recourse: definitions, formulations, solutions, and prospects

AH Karimi, G Barthe, B Schölkopf, I Valera - arxiv preprint arxiv …, 2020‏ - arxiv.org
Machine learning is increasingly used to inform decision-making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …

The hidden assumptions behind counterfactual explanations and principal reasons

S Barocas, AD Selbst, M Raghavan - … of the 2020 conference on fairness …, 2020‏ - dl.acm.org
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 …

How explainability contributes to trust in AI

A Ferrario, M Loi - Proceedings of the 2022 ACM Conference on …, 2022‏ - dl.acm.org
We provide a philosophical explanation of the relation between artificial intelligence (AI)
explainability and trust in AI, providing a case for expressions, such as “explainability fosters …

Disentangling fairness perceptions in algorithmic decision-making: the effects of explanations, human oversight, and contestability

M Yurrita, T Draws, A Balayn, D Murray-Rust… - Proceedings of the …, 2023‏ - dl.acm.org
Recent research claims that information cues and system attributes of algorithmic decision-
making processes affect decision subjects' fairness perceptions. However, little is still known …