{"total":405,"rows":[{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751,"area":null},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390,"area":null},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293,"area":null},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117,"area":null},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92,"area":null},{"id":"2102.08504","title":"Label Leakage and Protection in Two-party Split Learning","created":"2021-02-17","cited_by_count":90,"area":null},{"id":"2306.02050","title":"Provable Dynamic Fusion for Low-Quality Multimodal Data","created":"2023-06-03","cited_by_count":82,"area":null},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75,"area":null},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2210.16133","title":"Stop Measuring Calibration When Humans Disagree","created":"2022-10-28","cited_by_count":71,"area":null},{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71,"area":null},{"id":"2208.11640","title":"Repair Is Nearly Generation: Multilingual Program Repair with LLMs","created":"2022-08-24","cited_by_count":68,"area":null},{"id":"2210.01725","title":"MEDFAIR: Benchmarking Fairness for Medical Imaging","created":"2022-10-04","cited_by_count":68,"area":null},{"id":"2203.07835","title":"Better Uncertainty Calibration via Proper Scores for Classification and Beyond","created":"2022-03-15","cited_by_count":65,"area":null},{"id":"2210.03736","title":"Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis","created":"2022-10-05","cited_by_count":63,"area":null},{"id":"2309.12236","title":"Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing","created":"2023-09-21","cited_by_count":63,"area":null},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60,"area":null},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57,"area":null},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"area":null},{"id":"2211.16886","title":"A Unifying Theory of Distance from Calibration","created":"2022-11-30","cited_by_count":53,"area":null},{"id":"2203.12609","title":"Improving the Fairness of Chest X-ray Classifiers","created":"2022-03-23","cited_by_count":52,"area":null},{"id":"2203.13834","title":"A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration","created":"2022-03-25","cited_by_count":49,"area":null},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"area":null},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49,"area":null},{"id":"2101.02833","title":"Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition","created":"2021-01-08","cited_by_count":48,"area":null},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48,"area":null},{"id":"2102.12182","title":"Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration","created":"2021-02-24","cited_by_count":48,"area":null},{"id":"2207.06211","title":"Sample-dependent Adaptive Temperature Scaling for Improved Calibration","created":"2022-07-13","cited_by_count":48,"area":null},{"id":"2107.08353","title":"Top-label calibration and multiclass-to-binary reductions","created":"2021-07-18","cited_by_count":46,"area":null},{"id":"2101.06536","title":"Deep Cox Mixtures for Survival Regression","created":"2021-01-16","cited_by_count":44,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"area":null},{"id":"2404.03163","title":"Uncertainty in Language Models: Assessment through Rank-Calibration","created":"2024-04-04","cited_by_count":41,"area":null},{"id":"2108.01634","title":"Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation","created":"2021-08-03","cited_by_count":40,"area":null},{"id":"2201.13291","title":"Metrics for saliency map evaluation of deep learning explanation methods","created":"2022-01-31","cited_by_count":40,"area":null},{"id":"2102.07856","title":"Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification","created":"2021-02-15","cited_by_count":39,"area":null},{"id":"2111.03874","title":"Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective","created":"2021-11-06","cited_by_count":39,"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":"2210.00173","title":"Predictive Inference with Feature Conformal Prediction","created":"2022-10-01","cited_by_count":34,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2305.13665","title":"Dual Focal Loss for Calibration","created":"2023-05-23","cited_by_count":33,"area":null},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2205.09680","title":"Metrics of calibration for probabilistic predictions","created":"2022-05-19","cited_by_count":32,"area":null},{"id":"2104.05788","title":"Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30,"area":null},{"id":"2106.09613","title":"Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error","created":"2021-06-17","cited_by_count":29,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2102.10809","title":"Local Calibration: Metrics and Recalibration","created":"2021-02-22","cited_by_count":24,"area":null},{"id":"2109.03480","title":"Estimating Expected Calibration Errors","created":"2021-09-08","cited_by_count":24,"area":null},{"id":"2203.01850","title":"T-Cal: An optimal test for the calibration of predictive models","created":"2022-03-03","cited_by_count":24,"area":null},{"id":"2206.00050","title":"FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation","created":"2022-05-31","cited_by_count":24,"area":null},{"id":"2208.00461","title":"Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks","created":"2022-07-31","cited_by_count":24,"area":null},{"id":"2507.19264","title":"SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality","created":"2025-07-25","cited_by_count":23,"area":null},{"id":"2312.04021","title":"A Study on the Calibration of In-context Learning","created":"2023-12-07","cited_by_count":22,"area":null},{"id":"2306.08913","title":"Advancing Volumetric Medical Image Segmentation via Global-Local Masked Autoencoder","created":"2023-06-15","cited_by_count":21,"area":null},{"id":"2306.12306","title":"Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift","created":"2023-06-21","cited_by_count":20,"area":null},{"id":"2501.19047","title":"Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","created":"2025-01-31","cited_by_count":20,"area":null},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20,"area":null},{"id":"2106.05508","title":"Vertical Federated Learning without Revealing Intersection Membership","created":"2021-06-10","cited_by_count":19,"area":null},{"id":"2109.05263","title":"Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition","created":"2021-09-11","cited_by_count":19,"area":null},{"id":"2202.10847","title":"UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography","created":"2022-02-22","cited_by_count":19,"area":null},{"id":"2307.00934","title":"Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration","created":"2023-07-03","cited_by_count":19,"area":null},{"id":"2107.11091","title":"Class-Incremental Domain Adaptation with Smoothing and Calibration for Surgical Report Generation","created":"2021-07-23","cited_by_count":18,"area":null},{"id":"2210.01964","title":"The Calibration Generalization Gap","created":"2022-10-05","cited_by_count":18,"area":null},{"id":"2302.03686","title":"Long Horizon Temperature Scaling","created":"2023-02-07","cited_by_count":18,"area":null},{"id":"2306.04590","title":"Proximity-Informed Calibration for Deep Neural Networks","created":"2023-06-07","cited_by_count":18,"area":null},{"id":"2106.03761","title":"FairCal: Fairness Calibration for Face Verification","created":"2021-06-07","cited_by_count":17,"area":null},{"id":"2112.12004","title":"Barely-Supervised Learning: Semi-Supervised Learning with very few labeled images","created":"2021-12-22","cited_by_count":17,"area":null},{"id":"2206.14554","title":"Uncertainty-aware Panoptic Segmentation","created":"2022-06-29","cited_by_count":17,"area":null},{"id":"2202.01851","title":"A Note on \"Assessing Generalization of SGD via Disagreement\"","created":"2022-02-03","cited_by_count":16,"area":null},{"id":"2209.05355","title":"Analysis and Comparison of Classification Metrics","created":"2022-09-12","cited_by_count":16,"area":null},{"id":"2303.11298","title":"Reliability in Semantic Segmentation: Are We on the Right Track?","created":"2023-03-20","cited_by_count":16,"area":null},{"id":"2406.07212","title":"Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Models","created":"2024-06-11","cited_by_count":16,"area":null},{"id":"2301.01054","title":"Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise","created":"2023-01-03","cited_by_count":15,"area":null},{"id":"2304.09270","title":"Coarse race data conceals disparities in clinical risk score performance","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2308.11911","title":"ACLS: Adaptive and Conditional Label Smoothing for Network Calibration","created":"2023-08-23","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":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15,"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":"2310.19272","title":"NPCL: Neural Processes for Uncertainty-Aware Continual Learning","created":"2023-10-30","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":"2112.09368","title":"Improving evidential deep learning via multi-task learning","created":"2021-12-17","cited_by_count":13,"area":null},{"id":"2306.00876","title":"Quantifying Deep Learning Model Uncertainty in Conformal Prediction","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2402.05806","title":"On Temperature Scaling and Conformal Prediction of Deep Classifiers","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2405.15047","title":"Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2407.06844","title":"Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration","created":"2024-07-09","cited_by_count":13,"area":null},{"id":"2407.15773","title":"STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay","created":"2024-07-22","cited_by_count":13,"area":null},{"id":"2410.19780","title":"Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2503.14749","title":"Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence","created":"2025-03-18","cited_by_count":13,"area":null},{"id":"2302.08851","title":"On (assessing) the fairness of risk score models","created":"2023-02-17","cited_by_count":12,"area":null}],"next_cursor":"100"}