SIREN corrects winner's curse bias in adaptive LLM benchmarking via selection-aware repeated splits and bootstrap for valid procedure-level confidence intervals.
A framework for ef- ficient model evaluation through stratification, sampling, and estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
SIREN corrects winner's curse bias in adaptive LLM benchmarking via selection-aware repeated splits and bootstrap for valid procedure-level confidence intervals.