Tag
This paper proposes a unified optimization framework to explain misclassifications and assess classifier robustness by sparse, interpretable instance alterations and a Tolerance Region Confusion Matrix.
This paper introduces a human-in-the-loop framework for personalized algorithmic recourse that iteratively approximates a user's causal model through Bayesian inference, improving the plausibility and cost-effectiveness of recommendations.
This paper proposes Profit-Based Counterfactual Explanation (PBCE), a framework that formulates counterfactual explanation as a profit maximization problem for management and marketing, applied to manga sales in Japan.
This paper introduces PACE, a modular neuro-symbolic framework that combines a neural predictive model with symbolic reasoning to generate counterfactual explanations that respect domain-specific feasibility constraints. A case study on the Adult Income dataset demonstrates that incorporating symbolic rules yields more plausible and actionable explanations.
Introduces P²CE, a model-agnostic algorithm for generating plausible Pareto-optimal counterfactual explanations that balances feasibility, plausibility, and computational efficiency using an isolation forest outlier detector and SHAP values.
This paper examines counterfactual behavior in ML models through a geometric lens, showing that models with similar predictive performance can differ substantially in counterfactual outcomes due to the interaction between decision-boundary proximity and local data support. The findings identify counterfactual behavior as a distinct dimension from predictive performance, with implications for model selection and reliability of counterfactual explanation methods.
This paper introduces Counterfactual Explanation Consistency (CEC), a framework to detect and mitigate hidden procedural bias in outcome-fair models by aligning feature attributions between individuals and their counterfactual counterparts, with experiments on credit and income datasets.
The paper introduces Macro, a preference alignment framework using DPO to improve the validity and minimality of self-generated counterfactual explanations across multiple languages.