Dataset and Supplementary Materials for: Bridging Trust and Performance in Intelligent Systems: Hybrid Explainable AI Approaches for Interpreting Large Language Models

This repository contains the minimal dataset and reproducibility materials for the manuscript titled: "Bridging Trust and Performance in Intelligent Systems: Hybrid Explainable AI Approaches for Interpreting Large Language Models" Contents: 1. insertion_deletion_scores.csv Raw fidelity scores used to compute insertion and deletion metrics. 2. user_study_ratings.csv Anonymized Likert-scale responses from 15 participants evaluating explanation clarity, usefulness, and trust. 3. runtime_metrics.csv Computational cost and execution time measurements. 4. minimal_repro_script.txt Parameter settings and evaluation configuration details. All data are anonymized. No personally identifiable information is included. The materials are sufficient to reproduce the experimental results reported in the manuscript.