Hybrid interpretable models show substantial ICD across groups that can be reduced by coverage constraints with little accuracy loss.
Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A conditional invariance framework defines explanation fairness as explanations being statistically independent of protected attributes given task-relevant features, unifying existing metrics and enabling procedural bias audits.
citing papers explorer
-
When Interpretability Is Unequally Distributed: Fairness in Hybrid Interpretable Models
Hybrid interpretable models show substantial ICD across groups that can be reduced by coverage constraints with little accuracy loss.
-
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
A conditional invariance framework defines explanation fairness as explanations being statistically independent of protected attributes given task-relevant features, unifying existing metrics and enabling procedural bias audits.