A Synthetic Ground-Truth Framework for the Evaluation of Explainable AI Methods

用于评估可解释人工智能（XAI）方法的合成基准真值框架

Abstract: Evaluating explainable Artificial Intelligence (XAI) methods is a challenging task due to the lack of reliable evaluation procedures and, in particular, the absence of ground truth explanations. 摘要： 由于缺乏可靠的评估程序，特别是缺乏基准真值（ground truth）解释，评估可解释人工智能（XAI）方法是一项极具挑战性的任务。

In the literature, existing evaluation approaches typically assess explanations by measuring their fidelity with respect to the predictions of a black-box model. However, such evaluation strategies only quantify the degree to which an explanation reproduces the model’s output, without ensuring that the explanation correctly reflects the underlying decision process. 在现有文献中，评估方法通常通过测量解释与黑盒模型预测结果之间的保真度（fidelity）来进行评估。然而，此类评估策略仅量化了解释重现模型输出的程度，却无法确保该解释能正确反映底层的决策过程。

As a consequence, different explanations may achieve similar fidelity scores while providing inconsistent or misleading interpretations of the model behavior. 因此，不同的解释可能会获得相似的保真度分数，但却对模型行为提供了不一致或具有误导性的解读。

In this paper, we propose a framework for the evaluation of XAI methods based on synthetic ground truth. The proposed approach relies on controlled interventions to generate synthetic datasets in which the importance of input components can be determined by design. 在本文中，我们提出了一种基于合成基准真值的 XAI 方法评估框架。该方法依赖于受控干预来生成合成数据集，其中输入组件的重要性可以通过设计来确定。

This enables the construction of ground truth explanations that are directly aligned with the behavior of the model under analysis. The framework is instantiated across three data domains, namely binary images, tabular data, and time series, allowing a comprehensive assessment of explanation methods in heterogeneous settings. 这使得构建与被分析模型行为直接对齐的基准真值解释成为可能。该框架在三个数据领域（即二值图像、表格数据和时间序列）中进行了实例化，从而能够在异构环境下对解释方法进行全面评估。

Experimental results obtained by evaluating nine widely used XAI methods show significant limitations in current techniques and highlight the importance of synthetic, intervention-based benchmarks for a reliable assessment of explanation quality. 通过对九种广泛使用的 XAI 方法进行评估，实验结果显示了当前技术存在的显著局限性，并强调了基于合成干预的基准测试对于可靠评估解释质量的重要性。