Calibration of a model under the exact perturbations used by an explanation method improves explanation fidelity, and ReCalX achieves this with per-perturbation-strength temperature scaling.
Learning to explain: An information-theoretic perspective on model interpretation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
Calibration of a model under the exact perturbations used by an explanation method improves explanation fidelity, and ReCalX achieves this with per-perturbation-strength temperature scaling.