Developing and Experimenting on Approaches to Explainability in AI Systems
Developing and Experimenting on Approaches to Explainability in AI Systems
复制标题
DOI：
10.5220/0010900300003116
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Yuhao Zhang;Kevin McAreavey;Weiru Liu
中科院分区：
文献类型：
--
作者：
Yuhao Zhang;Kevin McAreavey;Weiru Liu
：关于可解释人工智能(XAI)的研究活动急剧增加，特别是在机器学习(ML)的背景下。然而，在涉及非专家利益相关者的人工智能环境中开发和实施XAI技术方面进展较少。本文报道了我们对向非专家提供ML算法结果的解释的研究。我们研究了三种解释方法(全局、局部和反事实)的使用，将决策树视为用例ML模型。我们用一个样本数据集演示了这些方法，并提供了一项涉及200多名参与者的研究的经验结果。我们的结果表明，大多数参与者对生成的解释都有很好的理解。
: There has been a sharp rise in research activities on explainable artificial intelligence (XAI), especially in the context of machine learning (ML). However, there has been less progress in developing and implementing XAI techniques in AI-enabled environments involving non-expert stakeholders. This paper reports our investigations into providing explanations on the outcomes of ML algorithms to non-experts. We investigate the use of three explanation approaches (global, local, and counterfactual), considering decision trees as a use case ML model. We demonstrate the approaches with a sample dataset, and provide empirical results from a study involving over 200 participants. Our results show that most participants have a good understanding of the generated explanations.