{"total":291,"rows":[{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600,"area":null},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252,"area":null},{"id":"2105.01879","title":"MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space","created":"2021-05-05","cited_by_count":233,"area":null},{"id":"2111.09805","title":"DICE: Leveraging Sparsification for Out-of-Distribution Detection","created":"2021-11-18","cited_by_count":166,"area":null},{"id":"2303.02966","title":"Non-Parametric Outlier Synthesis","created":"2023-03-06","cited_by_count":129,"area":null},{"id":"2107.11277","title":"Machine Learning with a Reject Option: A survey","created":"2021-07-23","cited_by_count":109,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2112.00787","title":"Provable Guarantees for Understanding Out-of-distribution Detection","created":"2021-12-01","cited_by_count":78,"area":null},{"id":"2103.08902","title":"Differentiable Learning Under Triage","created":"2021-03-16","cited_by_count":76,"area":null},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72,"area":null},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66,"area":null},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66,"area":null},{"id":"2205.05878","title":"Training Uncertainty-Aware Classifiers with Conformalized Deep Learning","created":"2022-05-12","cited_by_count":64,"area":null},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60,"area":null},{"id":"2404.10960","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","created":"2024-04-16","cited_by_count":54,"area":null},{"id":"2106.02395","title":"DOCTOR: A Simple Method for Detecting Misclassification Errors","created":"2021-06-04","cited_by_count":53,"area":null},{"id":"2105.00203","title":"Adversarial Example Detection for DNN Models: A Review and Experimental Comparison","created":"2021-05-01","cited_by_count":52,"area":null},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52,"area":null},{"id":"2206.00423","title":"Open-environment Machine Learning","created":"2022-06-01","cited_by_count":48,"area":null},{"id":"2310.14774","title":"Principled Approaches for Learning to Defer with Multiple Experts","created":"2023-10-23","cited_by_count":38,"area":null},{"id":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37,"area":null},{"id":"2202.03101","title":"Nonparametric Uncertainty Quantification for Single Deterministic Neural Network","created":"2022-02-07","cited_by_count":36,"area":null},{"id":"2310.14772","title":"Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms","created":"2023-10-23","cited_by_count":36,"area":null},{"id":"2402.03502","title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","created":"2024-02-05","cited_by_count":36,"area":null},{"id":"2302.11874","title":"What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers","created":"2023-02-23","cited_by_count":35,"area":null},{"id":"2110.15403","title":"Selective Regression Under Fairness Criteria","created":"2021-10-28","cited_by_count":34,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2310.14770","title":"Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention","created":"2023-10-23","cited_by_count":32,"area":null},{"id":"2403.19494","title":"Regression with Multi-Expert Deferral","created":"2024-03-28","cited_by_count":29,"area":null},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27,"area":null},{"id":"2207.07506","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2407.13732","title":"Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer","created":"2024-07-18","cited_by_count":26,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2206.09034","title":"Towards Better Selective Classification","created":"2022-06-17","cited_by_count":25,"area":null},{"id":"2306.08751","title":"Improving Selective Visual Question Answering by Learning from Your Peers","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2202.05613","title":"CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning","created":"2022-02-11","cited_by_count":24,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","cited_by_count":20,"area":null},{"id":"2110.13741","title":"Disrupting Deep Uncertainty Estimation Without Harming Accuracy","created":"2021-10-26","cited_by_count":19,"area":null},{"id":"2212.02742","title":"A Learning Based Hypothesis Test for Harmful Covariate Shift","created":"2022-12-06","cited_by_count":19,"area":null},{"id":"2401.03482","title":"Uncertainty Quantification on Clinical Trial Outcome Prediction","created":"2024-01-07","cited_by_count":19,"area":null},{"id":"2101.08732","title":"Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning","created":"2021-01-21","cited_by_count":17,"area":null},{"id":"2203.02586","title":"Concept-based Explanations for Out-Of-Distribution Detectors","created":"2022-03-04","cited_by_count":16,"area":null},{"id":"2305.15508","title":"How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2506.20650","title":"Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer","created":"2025-06-25","cited_by_count":16,"area":null},{"id":"2508.12491","title":"Cost-Aware Contrastive Routing for LLMs","created":"2025-08-17","cited_by_count":16,"area":null},{"id":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"area":null},{"id":"2312.14452","title":"How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?","created":"2023-12-22","cited_by_count":15,"area":null},{"id":"2105.14785","title":"Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart","created":"2021-05-31","cited_by_count":14,"area":null},{"id":"2301.12386","title":"Plugin estimators for selective classification with out-of-distribution detection","created":"2023-01-29","cited_by_count":14,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2609.24052","title":"Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)","created":"2026-09-21","cited_by_count":14,"area":null},{"id":"2210.10703","title":"AUC-based Selective Classification","created":"2022-10-19","cited_by_count":13,"area":null},{"id":"2405.18902","title":"A Causal Framework for Evaluating Deferring Systems","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2510.26706","title":"Budgeted Multiple-Expert Deferral","created":"2025-10-30","cited_by_count":13,"area":null},{"id":"2111.10481","title":"PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing","created":"2021-11-19","cited_by_count":12,"area":null},{"id":"2405.05160","title":"Selective Classification Under Distribution Shifts","created":"2024-05-08","cited_by_count":12,"area":null},{"id":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2311.04550","title":"Regression with Cost-based Rejection","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2403.14715","title":"Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2512.12844","title":"Selective Conformal Risk Control","created":"2025-12-14","cited_by_count":11,"area":null},{"id":"2103.03945","title":"SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Models","created":"2021-03-05","cited_by_count":10,"area":null},{"id":"2208.14660","title":"Unifying Evaluation of Machine Learning Safety Monitors","created":"2022-08-31","cited_by_count":10,"area":null},{"id":"2307.05350","title":"Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat","created":"2023-07-07","cited_by_count":10,"area":null},{"id":"2103.05354","title":"Revisiting Model's Uncertainty and Confidences for Adversarial Example Detection","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2104.08236","title":"Controlled abstention neural networks for identifying skillful predictions for regression problems","created":"2021-04-16","cited_by_count":9,"area":null},{"id":"2110.14243","title":"Online Selective Classification with Limited Feedback","created":"2021-10-27","cited_by_count":9,"area":null},{"id":"2305.13189","title":"Unsupervised Anomaly Detection with Rejection","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2406.04745","title":"Confidence-aware Contrastive Learning for Selective Classification","created":"2024-06-07","cited_by_count":8,"area":null},{"id":"2304.04906","title":"Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2402.06287","title":"AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems","created":"2024-02-09","cited_by_count":7,"area":null},{"id":"2403.11532","title":"Out-of-Distribution Detection Should Use Conformal Prediction (and Vice-versa?)","created":"2024-03-18","cited_by_count":7,"area":null},{"id":"2404.11350","title":"Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2404.16954","title":"Taming False Positives in Out-of-Distribution Detection with Human Feedback","created":"2024-04-25","cited_by_count":7,"area":null},{"id":"2405.11533","title":"Hierarchical Selective Classification","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2405.18635","title":"When and How Does In-Distribution Label Help Out-of-Distribution Detection?","created":"2024-05-28","cited_by_count":6,"area":null},{"id":"2504.13429","title":"Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs","created":"2025-04-18","cited_by_count":6,"area":null},{"id":"2202.07506","title":"Confidence Threshold Neural Diving","created":"2022-02-15","cited_by_count":5,"area":null},{"id":"2305.10384","title":"Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2305.12793","title":"Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2305.18393","title":"Training Private Models That Know What They Don't Know","created":"2023-05-28","cited_by_count":5,"area":null},{"id":"2307.14729","title":"Understanding Silent Failures in Medical Image Classification","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2402.16300","title":"Conformalized Selective Regression","created":"2024-02-26","cited_by_count":5,"area":null},{"id":"2505.15008","title":"Know When to Abstain: Optimal Selective Classification with Likelihood Ratios","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2606.08517","title":"A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control","created":"2026-06-07","cited_by_count":5,"area":null},{"id":"2305.01139","title":"Stratified Adversarial Robustness with Rejection","created":"2023-05-02","cited_by_count":4,"area":null},{"id":"2308.03179","title":"Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2408.04851","title":"Your Classifier Can Be Secretly a Likelihood-Based OOD Detector","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2502.01459","title":"Learning to Partially Defer for Sequences","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2605.25133","title":"Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2606.29054","title":"When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation","created":"2026-06-27","cited_by_count":4,"area":null},{"id":"2104.08281","title":"Controlled abstention neural networks for identifying skillful predictions for classification problems","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2107.05780","title":"Detect and Defense Against Adversarial Examples in Deep Learning using Natural Scene Statistics and Adaptive Denoising","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2205.07154","title":"Evaluating Generalizability of Fine-Tuned Models for Fake News Detection","created":"2022-05-15","cited_by_count":3,"area":null},{"id":"2212.06828","title":"An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty","created":"2022-12-13","cited_by_count":3,"area":null},{"id":"2304.03870","title":"ASPEST: Bridging the Gap Between Active Learning and Selective Prediction","created":"2023-04-07","cited_by_count":3,"area":null},{"id":"2403.15260","title":"Hyperbolic Metric Learning for Visual Outlier Detection","created":"2024-03-22","cited_by_count":3,"area":null}],"next_cursor":"100"}