English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Counterfactual explanations (CFEs) are a popular approach in explainableartificial intelligence (xAI), highlighting changes to input data necessary foraltering a model's output. A CFE can either describe a scenario that is betterthan the factual state (upward CFE), or a scenario that is worse than thefactual state (downward CFE). However, potential benefits and drawbacks of thedirectionality of CFEs for user behavior in xAI remain unclear. The currentuser study (N=161) compares the impact of CFE directionality on behavior andexperience of participants tasked to extract new knowledge from an automatedsystem based on model predictions and CFEs. Results suggest that upward CFEsprovide a significant performance advantage over other forms of counterfactualfeedback. Moreover, the study highlights potential benefits of mixed CFEsimproving user performance compared to downward CFEs or no explanations. Inline with the performance results, users' explicit knowledge of the system isstatistically higher after receiving upward CFEs compared to downwardcomparisons. These findings imply that the alignment between explanation andtask at hand, the so-called regulatory fit, may play a crucial role indetermining the effectiveness of model explanations, informing future researchdirections in xAI. To ensure reproducible research, the entire code, underlyingmodels and user data of this study is openly available:https://github.com/ukuhl/DirectionalAlienZoo

For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI