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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Automated decision-making systems are becoming increasingly ubiquitous,motivating an immediate need for their explainability. However, it remainsunclear whether users know what insights an explanation offers and, moreimportantly, what information it lacks. We conducted an online study with 200participants to assess explainees' ability to realise known and unknowninformation for four representative explanations: transparent modelling,decision boundary visualisation, counterfactual explainability and featureimportance. Our findings demonstrate that feature importance and decisionboundary visualisation are the most comprehensible, but their limitations arenot necessarily recognised by the users. In addition, correct interpretation ofan explanation -- i.e., understanding known information -- is accompanied byhigh confidence, but a failure to gauge its limits -- thus grasp unknowninformation -- yields overconfidence; the latter phenomenon is especiallyprominent for feature importance and transparent modelling. Machine learningexplanations should therefore embrace their richness and limitations tomaximise understanding and curb misinterpretation.

Can Users Correctly Interpret Machine Learning Explanations and Simultaneously Identify Their Limitations?