ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
英文标题：ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
arXiv:2607.09649v1 Announce Type: new Abstract: Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework f
打开原文相关 1.6 · 机会 0
中文
arXiv:2607.09649v1 Announce Type: new Abstract: Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework f
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
arXiv:2607.09649v1 Announce Type: new Abstract: Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework f