Generating Causally Compliant Counterfactual Explanations using ASP
This addresses the need for interpretable and actionable explanations in AI systems, though it appears incremental as it builds on existing counterfactual methods by incorporating causal constraints.
The paper tackles the problem of generating realistic counterfactual explanations by introducing the CoGS approach, which produces causally compliant paths from negative to positive outcomes, with preliminary results indicating improved feasibility.
This research is focused on generating achievable counterfactual explanations. Given a negative outcome computed by a machine learning model or a decision system, the novel CoGS approach generates (i) a counterfactual solution that represents a positive outcome and (ii) a path that will take us from the negative outcome to the positive one, where each node in the path represents a change in an attribute (feature) value. CoGS computes paths that respect the causal constraints among features. Thus, the counterfactuals computed by CoGS are realistic. CoGS utilizes rule-based machine learning algorithms to model causal dependencies between features. The paper discusses the current status of the research and the preliminary results obtained.