Abstract
Explaining closed-source Large Language Model (LLM) outputs is challenging because API access prevents gradient-based attribution, while perturbation methods are costly and noisy when they depend on regenerated text. We introduce \textbf\{Rotary Positional Embedding Linear Local Interpretable Model-agnostic Explanations (RoPE-LIME)\}, an open-source extension of gSMILE that decouples reasoning fro