Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness

ArXi:2605.27879v1 Announce Type: new Explainable AI (XAI) helps users interpret model behavior and identify potential faults. Agentic XAI systems use Large Language Models (LLMs) to make explanations accessible through natural-language interaction, but they can also produce plausible yet unfaithful explanations. This risk arises because unreliable XAI outputs for complex models can be amplified by LLMs and mislead users. We propose Faithful Agentic XAI (FAX), a framework that improves explanation faithfulness through explicit verification.