ProfileXAI: User-Adaptive Explainable AI

TL;DR

ProfileXAI is a flexible framework that combines multiple explainers with retrieval-augmented LLMs to generate user-adaptive, high-quality explanations for medical datasets, balancing fidelity, robustness, and interpretability.

Contribution

It introduces a novel, domain-agnostic system that dynamically selects explainers and generates grounded narratives tailored to different user profiles.

Findings

LIME offers the best fidelity-robustness balance.

Anchor produces the sparsest, low-token explanations.

SHAP achieves the highest user satisfaction.

Abstract

ProfileXAI is a model- and domain-agnostic framework that couples post-hoc explainers (SHAP, LIME, Anchor) with retrieval - augmented LLMs to produce explanations for different types of users. The system indexes a multimodal knowledge base, selects an explainer per instance via quantitative criteria, and generates grounded narratives with chat-enabled prompting. On Heart Disease and Thyroid Cancer datasets, we evaluate fidelity, robustness, parsimony, token use, and perceived quality. No explainer dominates: LIME achieves the best fidelity-robustness trade-off (Infidelity $\le 0.30$, $L<0.7$ on Heart Disease); Anchor yields the sparsest, low-token rules; SHAP attains the highest satisfaction ($\bar{x}=4.1$). Profile conditioning stabilizes tokens ($\sigma \le 13\%$) and maintains positive ratings across profiles ($\bar{x}\ge 3.7$, with domain experts at $3.77$), enabling efficient and trustworthy explanations.