{"total":60,"rows":[{"id":"2310.14774","title":"Principled Approaches for Learning to Defer with Multiple Experts","created":"2023-10-23","cited_by_count":38,"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":"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":"2403.02683","title":"Learning to Defer to a Population: A Meta-Learning Approach","created":"2024-03-05","cited_by_count":27,"area":null},{"id":"2311.01106","title":"In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer","created":"2023-11-02","cited_by_count":26,"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":"2405.05968","title":"A Universal Growth Rate for Learning with Smooth Surrogate Losses","created":"2024-05-09","cited_by_count":24,"area":null},{"id":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18,"area":"moe"},{"id":"2410.15729","title":"A Two-Stage Learning-to-Defer Approach for Multi-Task Learning","created":"2024-10-21","cited_by_count":17,"area":null},{"id":"2502.13962","title":"Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering","created":"2025-02-19","cited_by_count":17,"area":"lr"},{"id":"2502.01027","title":"Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees","created":"2025-02-03","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":"2410.15761","title":"Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees","created":"2024-10-21","cited_by_count":15,"area":null},{"id":"2405.18902","title":"A Causal Framework for Evaluating Deferring Systems","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","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":"2403.06906","title":"Cost-Sensitive Learning to Defer to Multiple Experts with Workload Constraints","created":"2024-03-11","cited_by_count":12,"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":"2407.07003","title":"Learning to Complement and to Defer to Multiple Users","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2504.12988","title":"Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2510.08314","title":"To Ask or Not to Ask: Learning to Require Human Feedback","created":"2025-10-09","cited_by_count":6,"area":"alignment"},{"id":"2601.22538","title":"Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models","created":"2026-01-30","cited_by_count":6,"area":null},{"id":"2311.13172","title":"Learning to Complement with Multiple Humans","created":"2023-11-22","cited_by_count":5,"area":null},{"id":"2407.15786","title":"LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning","created":"2024-07-22","cited_by_count":5,"area":"lr"},{"id":"2510.10988","title":"Adversarial Robustness in One-Stage Learning-to-Defer","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2502.01459","title":"Learning to Partially Defer for Sequences","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2502.10533","title":"Identity-Free Deferral For Unseen Experts","created":"2025-02-14","cited_by_count":4,"area":null},{"id":"2312.13218","title":"FiFAR: A Fraud Detection Dataset for Learning to Defer","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2602.17144","title":"When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.14324","title":"Consistent Learning-to-Defer with Expert-Conditional Advice","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2604.00904","title":"Fatigue-Aware Learning to Defer via Constrained Optimisation","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2307.02932","title":"When No-Rejection Learning is Consistent for Regression with Rejection","created":"2023-07-06","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":"2501.13810","title":"Learning to Help in Multi-Class Settings","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2504.11284","title":"Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2509.12573","title":"No Need for Learning to Defer? A Training Free Deferral Framework to Multiple Experts through Conformal Prediction","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2604.27723","title":"Optimized Deferral for Imbalanced Settings","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2606.21399","title":"Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2406.14404","title":"Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE","created":"2024-06-20","cited_by_count":1,"area":"inference"},{"id":"2506.05636","title":"Bayesian Inference for Correlated Human Experts and Classifiers","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2509.22984","title":"From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascades","created":"2025-09-26","cited_by_count":1,"area":"distill"},{"id":"2604.12411","title":"DeferredSeg:A Multi-Expert Deferral Framework for Medical Image Segmentation","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2605.12340","title":"Online Learning-to-Defer with Varying Experts","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.19557","title":"Density-Ratio Losses for Post-Hoc Learning to Defer","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.12587","title":"Strategic Decision Support for AI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2608.07583","title":"RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2505.19220","title":"DeCoDe: Defer-and-Complement Decision-Making via Decoupled Concept Bottleneck Models","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2508.21495","title":"Rethinking Calibration for Early-Exit Neural Networks","created":"2025-08-29","cited_by_count":0,"area":"inference"},{"id":"2509.11520","title":"Know What You Don't Know: Selective Prediction for Early Exit DNNs","created":"2025-09-15","cited_by_count":0,"area":"inference"},{"id":"2510.19351","title":"Learning To Defer To A Population With Limited Demonstrations","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2604.26991","title":"People-Centred Medical Image Analysis via Fairness-Aware Human-AI Cooperation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.06339","title":"A Regime Theory of Controller Class Selection for LLM Action Decisions","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2606.04779","title":"Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.28317","title":"One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.14617","title":"Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.21953","title":"RACER: Role-Aligned Competence Estimation for Human-AI Routing","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.39818","title":"Should I stay or should I show? Learning to selectively disclose information","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00381","title":"OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.12666","title":"Incremental Retrieval-Augmented Generation for Human-in-the-Loop Decision Support","created":"2026-10-08","cited_by_count":0,"area":"rag"}],"next_cursor":null}