The Model Parameter Randomisation Test (MPRT) is highly recognised in the eXplainable Artificial Intelligence (XAI) community due to its fundamental evaluative criterion: explanations should be sensitive to the parameters of the model they seek to explain. However, recent studies have raised several methodological concerns for the empirical interpretation of MPRT. In response, we propose two modifications to the original test: Smooth MPRT and Efficient MPRT. The former reduces the impact of noise on evaluation outcomes via sampling, while the latter avoids the need for biased similarity measurements by re-interpreting the test through the increase in explanation complexity after full model randomisation. Our experiments show that these modifications enhance the metric reliability, facilitating a more trustworthy deployment of explanation methods.

翻译：模型参数随机化测试（MPRT）因其基础评估准则——可解释性应依赖于其所解释模型的参数——而在可解释人工智能（XAI）领域广受认可。然而，近期研究对MPRT实证解释的方法学提出了若干质疑。为此，我们提出原始测试的两项改进方案：平滑MPRT与高效MPRT。前者通过采样降低噪声对评估结果的影响，后者则通过全模型随机化后解释复杂度的增加重新解读测试，从而规避有偏相似性测量的需求。实验表明，这些改进增强了指标的可靠性，有助于更可信地部署解释方法。