selective classification

Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models NAACL 2025 LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data AAAI 2025 Optimal Zero-shot Regret Minimization for Selective Classification with Out-of-Distribution Detection UAI 2025 Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It ICLR 2025 Classification with Conceptual Safeguards ICLR 2024 Confidence-aware Contrastive Learning for Selective Classification ICML 2024 Hierarchical Selective Classification NeurIPS 2024 How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks UAI 2024 Learning model uncertainty as variance-minimizing instance weights ICLR 2024 Overcoming Common Flaws in the Evaluation of Selective Classification Systems NeurIPS 2024 Plugin estimators for selective classification with out-of-distribution detection ICLR 2024 A Model-Agnostic Heuristics for Selective Classification AAAI 2023 AUC-based Selective Classification AISTATS 2023 Hybrid Uncertainty Quantification for Selective Text Classification in Ambiguous Tasks ACL 2023 Learning Sample Difficulty from Pre-trained Models for Reliable Prediction NeurIPS 2023 Learning to Defer with Limited Expert Predictions AAAI 2023 Making Pre-trained Language Models both Task-solvers and Self-calibrators ACL 2023 On the Evaluation of Neural Selective Prediction Methods for Natural Language Processing ACL 2023 Optimal Strategies for Reject Option Classifiers JMLR 2023 Promoting Fairness in Classification of Quality of Medical Evidence ACL 2023 Stratified Adversarial Robustness with Rejection ICML 2023 Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification NeurIPS 2023 Topics in Selective Classification AAAI 2023 Towards Better Selective Classification ICLR 2023 Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models ICCV 2023