CoVeR is a cluster-aware conformal decoding method that claims full-sequence coverage for LLM outputs without the (1-alpha)^L decay of prior conformal beam search.
Chain-of-thought prompting elicits reasoning in large language models
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.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction
CoVeR is a cluster-aware conformal decoding method that claims full-sequence coverage for LLM outputs without the (1-alpha)^L decay of prior conformal beam search.