CDA is a training-free decoding method that weights parametric, contextual, and abstention distributions using null-prompt calibrated entropy, letting LLMs answer when they can and abstain when they cannot.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When to Speak, When to Abstain: Contrastive Decoding with Abstention
CDA is a training-free decoding method that weights parametric, contextual, and abstention distributions using null-prompt calibrated entropy, letting LLMs answer when they can and abstain when they cannot.