Cer-Eval certifies LLM evaluation with confidence intervals while using 20 to 40 percent fewer test points on MMLU, AlpacaEval, and MATH.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs
Cer-Eval certifies LLM evaluation with confidence intervals while using 20 to 40 percent fewer test points on MMLU, AlpacaEval, and MATH.