AINeutralarXiv – CS AI · Mar 47/103
🧠
Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
Researchers developed new selective classification methods using likelihood ratio tests based on the Neyman-Pearson lemma, allowing AI models to abstain from uncertain predictions. The approach shows superior performance across vision and language tasks, particularly under covariate shift scenarios where test data differs from training data.