CONFEX: Uncertainty-Aware Counterfactual Explanations with Conformal Guarantees

ICLR 2026 Conference Submission20314 Authors

Keywords: uncertainty quantification, conformal prediction, counterfactual explanations, algorithmic recourse

Abstract:

Counterfactual explanations (CFXs) provide human-understandable justifications
for model predictions, enabling actionable recourse and enhancing interpretabil-
ity. To be reliable, CFXs must avoid regions of high predictive uncertainty, where
explanations may be misleading or inapplicable. However, existing methods often
neglect uncertainty or lack principled mechanisms for incorporating it with formal
guarantees. We propose CONFEX, a novel method for generating uncertainty-
aware counterfactual explanations using Conformal Prediction (CP) and Mixed-
Integer Linear Programming (MILP). CONFEX explanations are designed to pro-
vide local coverage guarantees, addressing the issue that CFX generation violates
exchangeability. To do so, we develop a novel localised CP procedure that enjoys
an efficient MILP encoding by leveraging an offline tree-based partitioning of the
input space. This way, CONFEX generates CFXs with rigorous guarantees on
both predictive uncertainty and optimality. We evaluate CONFEX against state-
of-the-art methods across diverse benchmarks and metrics, demonstrating that our
uncertainty-aware approach yields robust and plausible explanations.

Primary Area: interpretability and explainable AI

Submission Number: 20314