Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations

Abstract: This position paper highlights a growing trend in Explainable AI (XAI) research where LLMs are used to translate outputs from explainability techniques, like feature-attribution weights, into a natural language explanation. While this approach may improve accessibility or readability for users, recent findings suggest that translating into human-like explanations does not necessarily enhance user understanding and may instead lead to overreliance on AI systems. When LLMs summarize XAI outputs without surfacing model limitations, uncertainties, or inconsistencies, they risk reinforcing the illusion of interpretability rather than fostering meaningful transparency. We argue that - instead of merely translating XAI outputs - LLMs should serve as constructive agitators, or devil's advocates, whose role is to actively interrogate AI explanations by presenting alternative interpretations, potential biases, training data limitations, and cases where the model's reasoning may break down. In this role, LLMs can facilitate users in engaging critically with AI systems and generated explanations, with the potential to reduce overreliance caused by misinterpreted or specious explanations.