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.
Aleatoric or epistemic? Does it matter? Structural Safety 2009;31:105–12
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Uncertainty trace profiles from LM reasoning traces predict correct final answers with AUROC up to 0.807 and enable early error detection using only initial tokens.
The mutual-information measure of epistemic uncertainty is not reducible by additional data, requiring a split into aleatoric, sample-reducible epistemic, and mechanism-reducible epistemic uncertainty.
KL divergence of attention heads from uniform distribution predicts LLM answer correctness across datasets and model families.
Systematic review of 370 publications classifies uncertainty representation in risk management into probabilistic, evidence-based/fuzzy, qualitative, graphical, and hybrid families, noting limited practical integration.
citing papers explorer
-
Epistemic Uncertainty Is Not the Reducible Kind
The mutual-information measure of epistemic uncertainty is not reducible by additional data, requiring a split into aleatoric, sample-reducible epistemic, and mechanism-reducible epistemic uncertainty.