Item Response Theory enables adaptive and fixed-subset item selection that reduces safety benchmark costs by 80-99.9% while preserving high correlation with full rankings.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Bayesian deep learning method rankings are unreliable under data scarcity, reversing across datasets and sample sizes, and a hierarchical Bayesian framework with predictive detectability curves is needed to assess evaluation sufficiency.
Kernel ridge regression combined with mRMR feature selection improves prediction of full benchmark scores from question subsets over existing efficient benchmarking techniques.
citing papers explorer
-
Efficient Safety Benchmarking via Item Response Theory
Item Response Theory enables adaptive and fixed-subset item selection that reduces safety benchmark costs by 80-99.9% while preserving high correlation with full rankings.
-
ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation
Bayesian deep learning method rankings are unreliable under data scarcity, reversing across datasets and sample sizes, and a hierarchical Bayesian framework with predictive detectability curves is needed to assess evaluation sufficiency.
-
Efficient Benchmarking Is Just Feature Selection and Multiple Regression
Kernel ridge regression combined with mRMR feature selection improves prediction of full benchmark scores from question subsets over existing efficient benchmarking techniques.