PUB - Publikationen an der Universität Bielefeld

Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI), highlighting changes to input data necessary for altering a model’s output. A CFE can either describe a scenario that is better than the factual state (upwardCFE), or a scenario that is worse than the factual state (downwardCFE). However, potential benefits and drawbacks of the directionality of CFEs for user behavior in xAI remain unclear. The current user study (N = 161) compares the impact of CFE directionality on behavior and experience of participants tasked to extract new knowledge from an automated system based on model predictions and CFEs. Results suggest thatupwardCFEs provide a significant performance advantage over other forms of counterfactual feedback. Moreover, the study highlights potential benefits ofmixedCFEs improving user performance compared todownwardCFEs or no explanations. In line with the performance results, users’ explicit knowledge of the system is statistically higher after receivingupwardCFEs compared todownwardcomparisons. These findings imply that the alignment between explanation and task at hand, the so-called regulatory fit, may play a crucial role in determining the effectiveness of model explanations, informing future research directions in (xAI). To ensure reproducible research, the entire code, underlying models and user data of this study is openly available: