LLM generations that resemble other generations for the same question are more likely to be correct, and this rule can be used to build competitive black-box confidence scores.
Selectively answering ambiguous questions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
LLM generations that resemble other generations for the same question are more likely to be correct, and this rule can be used to build competitive black-box confidence scores.