LogTokU splits token uncertainty into aleatoric and epistemic components from the top-K logits, enabling single-pass hallucination detection and uncertainty-guided decoding.
Larger and more instructable language models become less reliable,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Estimating LLM Uncertainty with Evidence
LogTokU splits token uncertainty into aleatoric and epistemic components from the top-K logits, enabling single-pass hallucination detection and uncertainty-guided decoding.