Can Users Correctly Interpret Machine Learning Explanations and Simultaneously Identify Their Limitations?
share
Automated decision-making systems are becoming increasingly ubiquitous, motivating an immediate need for their explainability. However, it remains unclear whether users know what insights an explanation offers and, more importantly, what information it lacks. We conducted an online study with 200 participants to assess explainees' ability to realise known and unknown information for four representative explanations: transparent modelling, decision boundary visualisation, counterfactual explainability and feature importance. Our findings demonstrate that feature importance and decision boundary visualisation are the most comprehensible, but their limitations are not necessarily recognised by the users. In addition, correct interpretation of an explanation – i.e., understanding known information – is accompanied by high confidence, but a failure to gauge its limits – thus grasp unknown information – yields overconfidence; the latter phenomenon is especially prominent for feature importance and transparent modelling. Machine learning explanations should therefore embrace their richness and limitations to maximise understanding and curb misinterpretation.
READ FULL TEXT