PREF-XAI: Preference-Based Personalized Rule Explanations of Black-Box Machine Learning Models

TL;DR

PREF-XAI introduces a preference-driven framework for personalized rule-based explanations of black-box models, enabling adaptive and user-specific interpretability in XAI.

Contribution

It presents a novel methodology combining rule-based explanations with formal preference learning to personalize and improve model interpretability.

Findings

Accurately reconstructs user preferences from limited feedback.

Identifies highly relevant explanations tailored to user criteria.

Discovers new explanatory rules beyond initial user input.

Abstract

Explainable artificial intelligence (XAI) has predominantly focused on generating model-centric explanations that approximate the behavior of black-box models. However, such explanations often overlook a fundamental aspect of interpretability: different users require different explanations depending on their goals, preferences, and cognitive constraints. Although recent work has explored user-centric and personalized explanations, most existing approaches rely on heuristic adaptations or implicit user modeling, lacking a principled framework for representing and learning individual preferences. In this paper, we consider Preference-Based Explainable Artificial Intelligence (PREF-XAI), a novel perspective that reframes explanation as a preference-driven decision problem. Within PREF-XAI, explanations are not treated as fixed outputs, but as alternatives to be evaluated and selected according to user-specific criteria. In the PREF-XAI perspective, here we propose a methodology that combines rule-based explanations with formal preference learning. User preferences are elicited through a ranking of a small set of candidate explanations and modeled via an additive utility function inferred using robust ordinal regression. Experimental results on real-world datasets show that PREF-XAI can accurately reconstruct user preferences from limited feedback, identify highly relevant explanations, and discover novel explanatory rules not initially considered by the user. Beyond the proposed methodology, this work establishes a connection between XAI and preference learning, opening new directions for interactive and adaptive explanation systems.