RealAC: A Domain-Agnostic Framework for Realistic and Actionable Counterfactual Explanations

TL;DR

RealAC is a flexible, domain-agnostic framework that generates realistic, feasible, and user-preferred counterfactual explanations by preserving complex feature dependencies without domain-specific knowledge.

Contribution

It introduces a novel approach that aligns joint feature distributions to preserve dependencies and allows user-defined feature freezing, enhancing realism and actionability.

Findings

Outperforms state-of-the-art baselines in realism and dependency preservation

Balances realism with actionability effectively

Demonstrates robustness across synthetic and real datasets

Abstract

Counterfactual explanations provide human-understandable reasoning for AI-made decisions by describing minimal changes to input features that would alter a model's prediction. To be truly useful in practice, such explanations must be realistic and feasible -- they should respect both the underlying data distribution and user-defined feasibility constraints. Existing approaches often enforce inter-feature dependencies through rigid, hand-crafted constraints or domain-specific knowledge, which limits their generalizability and ability to capture complex, nonlinear relations inherent in data. Moreover, they rarely accommodate user-specified preferences and suggest explanations that are causally implausible or infeasible to act upon. We introduce RealAC, a domain-agnostic framework for generating realistic and actionable counterfactuals. RealAC automatically preserves complex inter-feature dependencies without relying on explicit domain knowledge -- by aligning the joint distributions of feature pairs between factual and counterfactual instances. The framework also allows end-users to ``freeze'' attributes they cannot or do not wish to change by suppressing change in frozen features during optimization. Evaluations on three synthetic and two real datasets demonstrate that RealAC balances realism with actionability. Our method outperforms state-of-the-art baselines and Large Language Model-based counterfactual generation techniques in causal edge score, dependency preservation score, and IM1 realism metric and offers a solution for causality-aware and user-centric counterfactual generation.