Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SISA training lets RL ransomware detectors forget selected samples by retraining one shard, with under 0.05% F1 drop and much lower retraining cost than full retraining.
citing papers explorer
-
Inducing Artificial Uncertainty in Language Models
Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.
-
Privacy-Aware Machine Unlearning with SISA for Reinforcement Learning-Based Ransomware Detection
SISA training lets RL ransomware detectors forget selected samples by retraining one shard, with under 0.05% F1 drop and much lower retraining cost than full retraining.