{"total":100,"rows":[{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156,"area":null},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60,"area":null},{"id":"2306.05724","title":"Explaining Predictive Uncertainty with Information Theoretic Shapley Values","created":"2023-06-09","cited_by_count":36,"area":null},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2209.13578","title":"Learning When to Advise Human Decision Makers","created":"2022-09-27","cited_by_count":18,"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":"2410.15361","title":"A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators","created":"2024-10-20","cited_by_count":15,"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":"2308.03172","title":"Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibration","created":"2023-08-06","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":"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":"2401.14432","title":"A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams","created":"2024-01-25","cited_by_count":12,"area":null},{"id":"2207.01898","title":"\"Even if ...\" -- Diverse Semifactual Explanations of Reject","created":"2022-07-05","cited_by_count":11,"area":null},{"id":"2303.03577","title":"A Review of and Roadmap for Data Science and Machine Learning for the Neuropsychiatric Phenotype of Autism","created":"2023-03-07","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":"2210.08906","title":"A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities","created":"2022-10-17","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":"2404.00897","title":"Machine Learning Robustness: A Primer","created":"2024-04-01","cited_by_count":8,"area":null},{"id":"2205.07623","title":"Model Agnostic Local Explanations of Reject","created":"2022-05-16","cited_by_count":7,"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":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2503.03184","title":"PAC Learning with Improvements","created":"2025-03-05","cited_by_count":6,"area":null},{"id":"2604.27924","title":"Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future","created":"2026-04-30","cited_by_count":6,"area":null},{"id":"2202.12653","title":"Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection","created":"2022-02-25","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":"2310.18601","title":"Online Decision Mediation","created":"2023-10-28","cited_by_count":4,"area":null},{"id":"2403.10182","title":"Fast and reliable uncertainty quantification with neural network ensembles for industrial image classification","created":"2024-03-15","cited_by_count":4,"area":null},{"id":"2411.04342","title":"Classification with Conceptual Safeguards","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2501.05714","title":"How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond","created":"2025-01-10","cited_by_count":4,"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":"2302.00839","title":"Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2303.09989","title":"Finding Competence Regions in Domain Generalization","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2402.14585","title":"Bandits with Abstention under Expert Advice","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2405.18686","title":"Rejection via Learning Density Ratios","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2412.06869","title":"Safety Monitoring of Machine Learning Perception Functions: a Survey","created":"2024-12-09","cited_by_count":3,"area":null},{"id":"2506.21802","title":"Classification with Reject Option: Distribution-free Error Guarantees via Conformal Prediction","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2511.10370","title":"SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2208.06359","title":"A Case for Rejection in Low Resource ML Deployment","created":"2022-08-12","cited_by_count":2,"area":null},{"id":"2305.10564","title":"Counterfactually Comparing Abstaining Classifiers","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2408.06302","title":"Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2409.16253","title":"Learning To Help: Training Models to Assist Legacy Devices","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2410.02005","title":"FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2410.21952","title":"On the Robustness of Adversarial Training Against Uncertainty Attacks","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2503.18826","title":"Interpretable and Fair Mechanisms for Abstaining Classifiers","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2507.12900","title":"Knowing What You Cannot Explain: Learning to Reject Low-Quality Explanations","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2511.11413","title":"Multicalibration Yields Better Matchings","created":"2025-11-14","cited_by_count":2,"area":null},{"id":"2607.14817","title":"Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2112.08851","title":"Classification Under Ambiguity: When Is Average-K Better Than Top-K?","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2209.15157","title":"Rethinking and Recomputing the Value of Machine Learning Models","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2301.02909","title":"How to Allocate your Label Budget? Choosing between Active Learning and Learning to Reject in Anomaly Detection","created":"2023-01-07","cited_by_count":1,"area":null},{"id":"2308.08381","title":"Precision and Recall Reject Curves for Classification","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2402.10665","title":"Soft Dice Confidence: A Near-Optimal Confidence Estimator for Selective Prediction in Semantic Segmentation","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2405.19864","title":"Out-of-distribution Reject Option Method for Dataset Shift Problem in Early Disease Onset Prediction","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2405.20486","title":"Policy Trees for Prediction: Interpretable and Adaptive Model Selection for Machine Learning","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2406.01825","title":"Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2407.08973","title":"Integrating White and Black Box Techniques for Interpretable Machine Learning","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2407.14114","title":"A3Rank: Augmentation Alignment Analysis for Prioritizing Overconfident Failing Samples for Deep Learning Models","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2503.13113","title":"Exploring the Potential of Bilevel Optimization for Calibrating Neural Networks","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2503.19656","title":"Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2504.09330","title":"Regretful Decisions under Label Noise","created":"2025-04-12","cited_by_count":1,"area":null},{"id":"2505.05273","title":"A Connection Between Learning to Reject and Bhattacharyya Divergences","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.22843","title":"On the Reliability and Stability of Selective Methods in Malware Classification Tasks","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2511.04855","title":"Epistemic Reject Option Prediction","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2605.06479","title":"Risk-Controlled Post-Processing of Decision Policies","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.21179","title":"Rejections Based on Predictive Uncertainty Enable Reliable Routine Soil Spectroscopy","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2608.11541","title":"Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2206.13083","title":"Adversarial Example Detection in Deployed Tree Ensembles","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2301.08839","title":"A Trustworthiness Score to Evaluate DNN Predictions","created":"2023-01-21","cited_by_count":0,"area":null},{"id":"2306.04663","title":"U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2308.03376","title":"Robust Ordinal Regression for Subsets Comparisons with Interactions","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2311.09145","title":"Model Agnostic Explainable Selective Regression via Uncertainty Estimation","created":"2023-11-15","cited_by_count":0,"area":null},{"id":"2312.10107","title":"Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2405.07841","title":"Sample Selection Bias in Machine Learning for Healthcare","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2405.12412","title":"Assessing the Probabilistic Fit of Neural Regressors via Conditional Congruence","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2406.15268","title":"Towards Robust Training Datasets for Machine Learning with Ontologies: A Case Study for Emergency Road Vehicle Detection","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2406.17346","title":"Stacked Confusion Reject Plots (SCORE)","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2409.00706","title":"Abstaining Machine Learning -- Philosophical Considerations","created":"2024-09-01","cited_by_count":0,"area":null},{"id":"2410.12297","title":"Conjunction Subspaces Test for Conformal and Selective Classification","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2503.03443","title":"Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2505.23437","title":"Bounded-Abstention Pairwise Learning to Rank","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2506.13217","title":"Polyra Swarms: A Shape-Based Approach to Machine Learning","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2510.06007","title":"Uncertainty in Machine Learning","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.24368","title":"Filtering instances and rejecting predictions to obtain reliable models in healthcare","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2602.04714","title":"Bounded-Abstention Multi-horizon Time-series Forecasting","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.01266","title":"A Study on Building Efficient Zero-Shot Relation Extraction Models","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.01971","title":"LOCUS: A Distribution-Free Loss-Quantile Score for Risk-Aware Predictions","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.14096","title":"Concisely Explaining the Doubt: Minimum-Size Abductive Explanations for Linear Models with a Reject Option","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.23855","title":"Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.07805","title":"Flexible Routing via Uncertainty Decomposition","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14744","title":"Mechanical Enforcement for LLM Governance:Evidence of Governance-Task Decoupling in Financial Decision Systems","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.03704","title":"Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.31331","title":"Expected Gain-based Escalation in Vertical Federated Learning","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.11983","title":"Removable Defects: The Economics and Limits of Deliberate Deficiency","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.28248","title":"Uncertainty quantification for trustworthy deep learning: Methods and measures","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.16198","title":"Picking the Right Image to Classify: Reliable-Input Selection in Teledermatology","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.17977","title":"When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.16825","title":"Mean Accuracy Is the Wrong Estimand for a Release Decision","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}