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
6 Pith papers cite this work, alongside 2,374 external citations. Polarity classification is still indexing.
6
Pith papers citing it
2,374
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
years
2026 6roles
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.
For small AWJM process data, treating statistical curation as competing hypotheses, using multi-fold evaluation, and residual physics with GPs yields more stable rankings and calibrated uncertainty than single-split pure ML.
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
-
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.
-
Tracing Uncertainty in Language Model "Reasoning"
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.
-
Physics-Informed Machine Learning Under Small-Data Constraints: Lessons from Abrasive Waterjet Milling
For small AWJM process data, treating statistical curation as competing hypotheses, using multi-fold evaluation, and residual physics with GPs yields more stable rankings and calibrated uncertainty than single-split pure ML.
-
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.
-
Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals
KL divergence of attention heads from uniform distribution predicts LLM answer correctness across datasets and model families.
-
Methods for Uncertainty Representation in Risk Management: A Comparative Review and Decision-Oriented Framework
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.