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

2026-04-21

AI Summary

This work addresses a key limitation in existing explainable artificial intelligence (XAI) approaches, which predominantly adopt model-centric explanations and overlook individual differences among users in terms of goals, preferences, and cognitive capacities. The study reframes explanation generation as a preference-based decision problem and introduces, for the first time, a systematic integration of XAI with preference learning. It proposes a user-preference-driven explanation framework that leverages users’ ranking feedback on a small set of candidate rule-based explanations. By combining robust ordinal regression with additive utility modeling, the framework enables personalized explanation selection. Experimental results demonstrate that the method accurately reconstructs user preferences from limited interactions, not only identifying highly relevant explanations but also uncovering novel rules previously unconsidered by users, thereby significantly enhancing both the practical utility and personalization of explanations.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Explainable Artificial Intelligence
• Personalized Explanations
• User Preferences
• Preference Learning
• Black-Box Models

Innovation

• Preference-Based XAI
• Personalized Explanations
• Rule-Based Explanations
• Preference Learning
• Ordinal Regression