论文标题
解释性的功能：用户如何理解XAI中分类和连续特征的反事实和因果解释
Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI
论文作者
论文摘要
反事实解释越来越多地用于解决AI决策中的解释性，追索性和偏见。但是，我们不知道反事实解释如何帮助用户理解系统决策，因为没有大规模的用户研究将其疗效与因果解释（例如因果解释）（在基于规则和决策树模型中具有较长的使用记录）进行了比较。反事实解释对分类是否同样有效，而对于连续特征也尚不清楚，尽管当前方法认为它们是这样做的。因此，在对127名志愿者参与者的对照用户研究中，我们测试了反事实和因果解释对用户对简单AI系统做出的决策的客观准确性的影响，以及参与者对解释的满意度和信任的主观判断。我们发现了客观和主观措施之间的解离：反事实解释比无解释控制描述更高的预测准确性，但与因果关系的解释相比，准确性没有比因果解释更高，而相反的解释则比因果关系更高的满意度和信任。我们还发现，用户比涉及连续功能的用户更容易理解所涉及的分类功能的解释。我们讨论了这些发现对XAI中当前和未来反事实方法的含义。
Counterfactual explanations are increasingly used to address interpretability, recourse, and bias in AI decisions. However, we do not know how well counterfactual explanations help users to understand a systems decisions, since no large scale user studies have compared their efficacy to other sorts of explanations such as causal explanations (which have a longer track record of use in rule based and decision tree models). It is also unknown whether counterfactual explanations are equally effective for categorical as for continuous features, although current methods assume they do. Hence, in a controlled user study with 127 volunteer participants, we tested the effects of counterfactual and causal explanations on the objective accuracy of users predictions of the decisions made by a simple AI system, and participants subjective judgments of satisfaction and trust in the explanations. We discovered a dissociation between objective and subjective measures: counterfactual explanations elicit higher accuracy of predictions than no-explanation control descriptions but no higher accuracy than causal explanations, yet counterfactual explanations elicit greater satisfaction and trust than causal explanations. We also found that users understand explanations referring to categorical features more readily than those referring to continuous features. We discuss the implications of these findings for current and future counterfactual methods in XAI.
