Counterfactual explanations are an increasingly popular form of post hoc explanation due to their (i) applicability across problem domains, (ii) proposed legal compliance (e.g., with GDPR), and (iii) reliance on the contrastive nature of human explanation. Although counterfactual explanations are normally used to explain individual predictive-instances, we explore a novel use case in which groups of similar instances are explained in a collective fashion using ``group counterfactuals'' (e.g., to highlight a repeating pattern of illness in a group of patients). These group counterfactuals meet a human preference for coherent, broad explanations covering multiple events/instances. A novel, group-counterfactual algorithm is proposed to generate high-coverage explanations that are faithful to the to-be-explained model. This explanation strategy is also evaluated in a large, controlled user study (N=207), using objective (i.e., accuracy) and subjective (i.e., confidence, explanation satisfaction, and trust) psychological measures. The results show that group counterfactuals elicit modest but definite improvements in people's understanding of an AI system. The implications of these findings for counterfactual methods and for XAI are discussed.
翻译:反事实解释是一种越来越受欢迎的事后解释形式,因为它们具有以下特点:(i)适用于各种问题领域,(ii)符合法律要求(例如符合GDPR的要求),(iii)依赖于人类解释的对比性特质。虽然反事实解释通常用于解释单个预测实例,但我们探讨了一种新的用例,即使用“组-反事实环境”(Group-Counterfactuals)集体解释类似实例的组(例如,突出显示一组患者中疾病的重复模式)。这些组-反事实环境符合人类对涵盖多个事件/实例的一致,广泛解释的偏好。提出了一种新颖的组-反事实环境算法,用于生成高覆盖范围、忠于所要解释的模型的解释。这种解释策略也在大型受控用户研究中(N=207)得到了评估,使用客观(即准确性)和主观(即信心、解释满意度和信任)的心理测量。结果表明,组-反事实环境在人们理解AI系统方面带来了明显的改善。讨论了这些发现对反事实方法和XAI的影响。