TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.
Position: Uncertainty quantification needs reassessment for large-language model agents,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A survey that categorizes uncertainty quantification approaches for graphical models into representation and handling dimensions to identify challenges and opportunities.
citing papers explorer
-
TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.
-
Uncertainty Quantification on Graph Learning: A Survey
A survey that categorizes uncertainty quantification approaches for graphical models into representation and handling dimensions to identify challenges and opportunities.