A Bayesian interval-ranking method using anchor models yields probabilistic LLM rankings that the authors show remain discriminative down to roughly 20 questions.
Improving language understand- ing by generative pre-training
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
-
Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges
A Bayesian interval-ranking method using anchor models yields probabilistic LLM rankings that the authors show remain discriminative down to roughly 20 questions.