BoolXLLM: LLM-Assisted Explainability for Boolean Models

TL;DR

BoolXLLM introduces a hybrid approach integrating LLMs into Boolean rule learning to enhance interpretability and accessibility of explanations for non-technical users, while maintaining competitive accuracy.

Contribution

This work presents a novel framework that combines LLMs with Boolean rule-based classifiers to improve feature selection, rule interpretation, and explanation accessibility.

Findings

LLM-assisted feature selection improves domain relevance.

Semantic discretization strategies are effectively proposed by LLMs.

Early results show enhanced interpretability with maintained predictive performance.

Abstract

Interpretable machine learning aims to provide transparent models whose decision-making processes can be readily understood by humans. Recent advances in rule-based approaches, such as expressive Boolean formulas (BoolXAI), offer faithful and compact representations of model behavior. However, for non-technical stakeholders, main challenges remain in practice: (i) selecting semantically meaningful features and (ii) translating formal logical rules into accessible explanations. In this work, we propose BoolXLLM , as a hybrid framework that integrates Large Language Models (LLMs) into the end-to-end pipeline of Boolean rule learning. We augment BoolXAI , an expressive Boolean rule-based classifier, with LLMs at three critical stages: (1) feature selection, where LLMs guide the identification of domain-relevant variables; (2) threshold recommendation, where LLMs propose semantically meaningful discretization strategies for numerical features; and (3) rule compression and interpretation, where Boolean rules are translated into natural language explanations at both global and local levels. This integration bridges formal, faithful explanations with human-understandable narratives. This allows build an explainable AI system that is both theoretically grounded and accessible to non-experts. Early empirical results demonstrate that LLM-assisted pipelines improve interpretability while maintaining competitive predictive performance. Our work highlights the promise of combining symbolic reasoning with language-based models for human-centered explainability.