Metric · Understanding model behaviour
Users get how it decides
What it tells you
Whether people can predict and explain what the AI will do with an input. The KU Leuven framework defines it as the user's ability to correctly interpret the model behaviour.
How, in 10 minutes
Two short comprehension questions per task, such as 'Why was this e-mail marked urgent?' scored against the actual reason, plus one confidence rating on the answer.
Benchmark
No benchmark yet. Run the kit and send us yours.
Plan your test explains how to choose metrics and how many participants you need.
Questionnaire items
- Why did the system give this result? (open answer, scored)
- What would the system do if the input changed in this way? (scored)
- How sure are you of your answer? (1 to 5)
Answer on a 1 to 7 scale from strongly disagree to strongly agree unless the item states its own scale. The ULTRA team wrote or adapted these items for the kits and has not checked their reliability, so report them as ULTRA kit items and name any questionnaire they were adapted from.
Log events
explanation_opened {pattern, item}explanation_time_ms {pattern, item}Pairs with
Research side · the property behind this metric
Property
References
- Donoso-Guzmán et al. 2025, Table 9: understanding model behaviour.
- Hoffman et al. 2018, Metrics for explainable AI.