{"total":46,"rows":[{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252,"area":null},{"id":"2202.03673","title":"Calibrated Learning to Defer with One-vs-All Classifiers","created":"2022-02-08","cited_by_count":69,"area":null},{"id":"2210.16955","title":"Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles","created":"2022-10-30","cited_by_count":60,"area":null},{"id":"2110.06177","title":"Tracking the risk of a deployed model and detecting harmful distribution shifts","created":"2021-10-12","cited_by_count":40,"area":null},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2405.17544","title":"Towards Human-AI Complementarity with Prediction Sets","created":"2024-05-27","cited_by_count":25,"area":null},{"id":"2405.05145","title":"Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty","created":"2024-04-16","cited_by_count":20,"area":null},{"id":"2402.07821","title":"On Computationally Efficient Multi-Class Calibration","created":"2024-02-12","cited_by_count":16,"area":null},{"id":"2411.02988","title":"Confidence Calibration of Classifiers with Many Classes","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2305.10886","title":"Minimum-Risk Recalibration of Classifiers","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2111.03135","title":"Scaffolding Sets","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2305.00070","title":"Online Platt Scaling with Calibeating","created":"2023-04-28","cited_by_count":8,"area":null},{"id":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2202.07825","title":"Reducing Overconfidence Predictions for Autonomous Driving Perception","created":"2022-02-16","cited_by_count":7,"area":null},{"id":"2304.05104","title":"Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networks","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2311.10018","title":"On the Overconfidence Problem in Semantic 3D Mapping","created":"2023-11-16","cited_by_count":7,"area":null},{"id":"2504.18395","title":"Three Types of Calibration with Properties and their Semantic and Formal Relationships","created":"2025-04-25","cited_by_count":5,"area":null},{"id":"2505.23804","title":"Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2204.13087","title":"Faster online calibration without randomization: interval forecasts and the power of two choices","created":"2022-04-27","cited_by_count":4,"area":null},{"id":"2210.03702","title":"Class-wise and reduced calibration methods","created":"2022-10-07","cited_by_count":4,"area":null},{"id":"2402.09326","title":"Stability and Multigroup Fairness in Ranking with Uncertain Predictions","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2501.11866","title":"Evaluating multiple models using labeled and unlabeled data","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2305.14696","title":"SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2404.16188","title":"Pearls from Pebbles: Improved Confidence Functions for Auto-labeling","created":"2024-04-24","cited_by_count":3,"area":null},{"id":"2410.07014","title":"Optimizing Estimators of Squared Calibration Errors in Classification","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2501.16756","title":"Random Forest Calibration","created":"2025-01-28","cited_by_count":3,"area":null},{"id":"2510.23471","title":"Robust Decision Making with Partially Calibrated Forecasts","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2512.09054","title":"Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2411.04276","title":"Labels in Extremes: How Well Calibrated are Extreme Multi-label Classifiers?","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2510.26566","title":"Multiclass Local Calibration with the Jensen-Shannon Distance","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2606.03245","title":"Hierarchies of Calibration: Classification meets Regression","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2608.10406","title":"Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection","created":"2026-08-11","cited_by_count":2,"area":null},{"id":"2509.12760","title":"Similarity-Distance-Magnitude Activations","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2509.23000","title":"Sample-efficient Multiclass Calibration under $\\ell_{p}$ Error","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.25458","title":"Scalable Utility-Aware Multiclass Calibration","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2205.14310","title":"Approximate Conditional Coverage & Calibration via Neural Model Approximations","created":"2022-05-28","cited_by_count":0,"area":null},{"id":"2207.06529","title":"Estimating Classification Confidence Using Kernel Densities","created":"2022-07-13","cited_by_count":0,"area":null},{"id":"2502.20167","title":"Similarity-Distance-Magnitude Universal Verification","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2505.23463","title":"Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2510.01987","title":"Private Federated Multiclass Post-hoc Calibration","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2603.07867","title":"Slumbering to Precision: Enhancing Artificial Neural Network Calibration Through Sleep-like Processes","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2607.08377","title":"Eigenvalue Calibration for Semantic Embeddings of Large Language Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.14089","title":"Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.01072","title":"Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}