Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making. Existing explanation ways mainly fall into two categories. Traditional explainable AI (XAI), such as gradient-based attribution, produces low-level attribution signals tightly coupled with model decisions, and harder to be understood by human than natural language explanations. Meanwhile, large language model (LLM)-based explanation generation often produces generic and ungrounded descriptions due to the lack of heuristic evidence and task-specific supervision, stemming from limited grounded explanation datasets for SDD. We therefore propose a training-free explanation framework that integrates XAI evidence with multimodal LLMs to generate grounded and specific explanations. Using the PartialSpoof dataset, we construct a grounded explanation dataset and show that methods with XAI increase inside accuracy by over 45\%, verified through human evaluation and faithfulness checks.

翻译：语音深度伪造检测（SDD）系统需要可信赖的解释以实现可靠的决策。现有解释方式主要分为两类：传统可解释人工智能（XAI），例如基于梯度的归因方法，可产生与模型决策紧密耦合的低层级归因信号，但较自然语言解释更难被人类理解；另一方面，基于大语言模型（LLM）的解释生成因缺乏启发性证据与任务特定监督，常生成泛化且无依据的描述，这源于SDD领域缺乏基于证据的解释数据集。为此，我们提出一种免训练解释框架，将XAI证据与多模态大语言模型相结合，以生成有依据且具体的解释。利用PartialSpoof数据集，我们构建了一个基于证据的解释数据集，并通过人工评估与可信度检验证明，融入XAI的方法将内部准确率提升了45%以上。