Counterfactual explanations and how to find them: literature review and benchmarking

R Guidotti - Data Mining and Knowledge Discovery, 2024‏ - Springer
Interpretable machine learning aims at unveiling the reasons behind predictions returned by
uninterpretable classifiers. One of the most valuable types of explanation consists of …

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 …

Interpretable machine learning: Fundamental principles and 10 grand challenges

C Rudin, C Chen, Z Chen, H Huang… - Statistic …, 2022‏ - projecteuclid.org
Interpretability in machine learning (ML) is crucial for high stakes decisions and
troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …

Evaluating the quality of machine learning explanations: A survey on methods and metrics

J Zhou, AH Gandomi, F Chen, A Holzinger - Electronics, 2021‏ - mdpi.com
The most successful Machine Learning (ML) systems remain complex black boxes to end-
users, and even experts are often unable to understand the rationale behind their decisions …

A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence

I Stepin, JM Alonso, A Catala, M Pereira-Fariña - Ieee Access, 2021‏ - ieeexplore.ieee.org
A number of algorithms in the field of artificial intelligence offer poorly interpretable
decisions. To disclose the reasoning behind such algorithms, their output can be explained …

Counterfactuals and causability in explainable artificial intelligence: Theory, algorithms, and applications

YL Chou, C Moreira, P Bruza, C Ouyang, J Jorge - Information Fusion, 2022‏ - Elsevier
Deep learning models have achieved high performance across different domains, such as
medical decision-making, autonomous vehicles, decision support systems, among many …

If only we had better counterfactual explanations: Five key deficits to rectify in the evaluation of counterfactual xai techniques

MT Keane, EM Kenny, E Delaney, B Smyth - arxiv preprint arxiv …, 2021‏ - arxiv.org
In recent years, there has been an explosion of AI research on counterfactual explanations
as a solution to the problem of eXplainable AI (XAI). These explanations seem to offer …

Counterfactual explanations and algorithmic recourses for machine learning: A review

S Verma, V Boonsanong, M Hoang, K Hines… - ACM Computing …, 2024‏ - dl.acm.org
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 …

Transparency, auditability, and explainability of machine learning models in credit scoring

M Bücker, G Szepannek, A Gosiewska… - Journal of the …, 2022‏ - Taylor & Francis
A major requirement for credit scoring models is to provide a maximally accurate risk
prediction. Additionally, regulators demand these models to be transparent and auditable …

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 …