FGNS ranks neighbor examples by weighted distance to a class prototype, letting non-experts detect AI misclassifications faster and more accurately than with standard k-NN explanations.
Proxy tasks and subjective measures can be misleading in eval- uating explainable ai systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Feature-Guided Neighbor Selection for Non-Expert Evaluation of Model Predictions
FGNS ranks neighbor examples by weighted distance to a class prototype, letting non-experts detect AI misclassifications faster and more accurately than with standard k-NN explanations.