Pre-hoc and Co-hoc Explainability: Novel Frameworks for Integrating Interpretability into Machine Learning Training for Enhanced Transparency and Performance
Cagla Acun, Olfa Nasraoui · Preprints.org · 2025
Despite ongoing efforts to make black-box machine learning models more explainable, transparent, and trustworthy, there is growing advocacy for using only inherently interpretable models for high-stakes decision-making. Post-hoc explanations have been criticized for learning surrogate models that may not accurately reflect the actual mechanisms of the original model and for adding computational burden at prediction time. We propose two novel explainability approaches to address these limitations: pre-hoc explainability and co-hoc explainability. These approaches integrate explanations derived from an inherently interpretable white-box model into the learning stage of the black-box model without compromising accuracy. Unlike post-hoc methods, our approach does not rely on random input perturbation or post-hoc training alone. We extend our pre-hoc and co-hoc frameworks to generate instance-specific explanations by incorporating the Jensen-Shannon divergence as a regularization term while capturing the local behavior of the black-box model. This extension provides local explanations that are faithful to the model’s behavior and consistent with the explanations generated by the global explainer model. Our two-phase approach first trains models for fidelity, then generates local explanations by fine-tuning the explainer model within the neighborhood of the instance being explained. Experiments on three benchmark datasets from different domains (credit risk scoring and movie recommendations) demonstrate the advantages of our techniques in terms of global and local fidelity without compromising accuracy. Our methods avoid the pitfalls of surrogate modeling, making them more scalable, robust, and reliable compared to post-hoc techniques like LIME. Additionally, our co-hoc learning framework enhances the accuracy of white-box models by up to 3%, highlighting its potential for applications in healthcare and legal decision-making where interpretable models are required. Our approaches provide more faithful and consistent explanations at a lower computational cost than existing methods, offering a promising direction for making machine learning models more transparent and trustworthy while maintaining high prediction accuracy.