Protocol choices in token-probability measurement and conditioning context make verbalized vs. token confidence comparisons sensitive, with Instruct models near parity under default generated-answer bare-context settings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Asking Is Not Enough: Protocol Sensitivity in LLM Confidence Calibration
Protocol choices in token-probability measurement and conditioning context make verbalized vs. token confidence comparisons sensitive, with Instruct models near parity under default generated-answer bare-context settings.