用因果理论评估布尔函数预测的可解释性工具，发现新方法更准。
Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulae
- 基于实际因果定义变量重要性，量化更精准
- 新工具B-ReX在随机10值布尔公式上误差仅0.072±0.012
- 适合研究模型可解释性与黑箱解释工具的学者
可解释人工智能（XAI）的评估具有挑战性，主要源于解释的主观性。本文聚焦表格数据与布尔函数取值预测这一具体场景，通过引入基于实际因果关系的变量重要性形式化度量，扩展了该领域的先前工作，并以此为基准评估当前主流黑箱XAI工具。我们提出一种新工具B-ReX，基于现有ReX工具改进，实验证明其在大规模基准测试中优于其他黑箱XAI方法。具体而言，B-ReX在随机10值布尔公式上的杰恩-申诺尔散度为0.072±0.012。
原文摘要 · Abstract (English)
Evaluating explainable AI (XAI) approaches is a challenging task in general, due to the subjectivity of explanations. In this paper, we focus on tabular data and the specific use case of AI models predicting the values of Boolean functions. We extend the previous work in this domain by proposing a formal and precise measure of importance of variables based on actual causality, and we evaluate state-of-the-art XAI tools against this measure. We also present a novel XAI tool B-ReX, based on the existing tool ReX, and demonstrate that it is superior to other black-box XAI tools on a large-scale benchmark. Specifically, B-ReX achieves a Jensen-Shannon divergence of 0.072 $\pm$ 0.012 on random 10-valued Boolean formulae
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。