Machine learning models that automate decision-making are increasingly used
in consequential areas such as loan approvals, pretrial bail approval, and
hiring. Unfortunately, most of these models are black boxes, i.e., they are
unable to reveal how they reach these prediction decisions. A need for
transparency demands justification for such predictions. An affected individual
might also desire explanations to understand why a decision was made. Ethical
and legal considerations require informing the individual of changes in the
input attribute (s) that could be made to produce a desirable outcome. Our work
focuses on the latter problem of generating counterfactual explanations by
considering the causal dependencies between features. In this paper, we present
the framework CFGs, CounterFactual Generation with s(CASP), which utilizes the
goal-directed Answer Set Programming (ASP) system s(CASP) to automatically
generate counterfactual explanations from models generated by rule-based
machine learning algorithms in particular. We benchmark CFGs with the FOLD-SE
model. Reaching the counterfactual state from the initial state is planned and
achieved using a series of interventions. To validate our proposal, we show how
counterfactual explanations are computed and justified by imagining worlds
where some or all factual assumptions are altered/changed. More importantly, we
show how CFGs navigates between these worlds, namely, go from our initial state
where we obtain an undesired outcome to the imagined goal state where we obtain
the desired decision, taking into account the causal relationships among
features.

自动决策的机器学习模型在贷款批准、预审保释批准和雇佣等重要领域中越来越常见。然而，大多数这些模型都是黑盒子，即无法透露如何做出预测决策的过程。因此，有必要提供解释来满足透明度需求，并使人们了解为何做出某个决策。我们的研究侧重于生成反事实解释的后问题，通过考虑特征之间的因果关系来解决。本文提出了 CFGs 框架，即 CounterFactual Generation with s (CASP)，它利用目标导向的 ASP 系统 s (CASP) 从基于规则的机器学习算法生成的模型中自动生成反事实解释。我们使用 FOLD-SE 模型对 CFGs 进行了基准测试，通过一系列干预来计划并实现从初始状态到反事实状态的转换。为了验证我们的提案，我们展示了如何计算和证明反事实解释，通过想象某些或所有事实假设被改变的世界。更重要的是，我们展示了 CFGs 在这些世界之间的导航能力，即从我们的初始状态（获得了不希望的结果）到想象中的目标状态（获得了期望的决策），考虑到特征之间的因果关系。