The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomes

TL;DR

This paper introduces semifactual explanations using 'even if...' reasoning to optimize positive outcomes in AI systems, demonstrating their effectiveness through causal formalisation, benchmark tests, and user studies.

Contribution

It pioneers the formalisation of semifactual explanations and shows they outperform counterfactuals in maximizing user benefit and perceived usefulness.

Findings

Algorithms effectively maximise gain with semifactuals

Causality enhances explanation quality

Users find semifactuals more useful than counterfactuals for positive outcomes

Abstract

When users receive either a positive or negative outcome from an automated system, Explainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes into positive ones by crossing a decision boundary using counterfactuals (e.g., \textit{"If you earn 2k more, we will accept your loan application"}). Here, we instead focus on \textit{positive} outcomes, and take the novel step of using XAI to optimise them (e.g., \textit{"Even if you wish to half your down-payment, we will still accept your loan application"}). Explanations such as these that employ "even if..." reasoning, and do not cross a decision boundary, are known as semifactuals. To instantiate semifactuals in this context, we introduce the concept of \textit{Gain} (i.e., how much a user stands to benefit from the explanation), and consider the first causal formalisation of semifactuals. Tests on benchmark datasets show our algorithms are better at maximising gain compared to prior work, and that causality is important in the process. Most importantly however, a user study supports our main hypothesis by showing people find semifactual explanations more useful than counterfactuals when they receive the positive outcome of a loan acceptance.