{"total":357,"rows":[{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751,"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":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252,"area":null},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212,"area":null},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134,"area":null},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2210.04714","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","created":"2022-10-10","cited_by_count":104,"area":null},{"id":"2107.10161","title":"Evidential Deep Learning for Open Set Action Recognition","created":"2021-07-21","cited_by_count":96,"area":null},{"id":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92,"area":null},{"id":"2111.15430","title":"The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration","created":"2021-11-30","cited_by_count":91,"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":"2403.14119","title":"C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion","created":"2024-03-21","cited_by_count":83,"area":"mllm"},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"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":"2205.05878","title":"Training Uncertainty-Aware Classifiers with Conformalized Deep Learning","created":"2022-05-12","cited_by_count":64,"area":null},{"id":"2207.10792","title":"Test-Time Adaptation via Self-Training with Nearest Neighbor Information","created":"2022-07-08","cited_by_count":64,"area":null},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63,"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":"2207.06211","title":"Sample-dependent Adaptive Temperature Scaling for Improved Calibration","created":"2022-07-13","cited_by_count":48,"area":null},{"id":"2210.07810","title":"A Consistent and Differentiable Lp Canonical Calibration Error Estimator","created":"2022-10-13","cited_by_count":47,"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":"2101.03453","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","created":"2021-01-10","cited_by_count":44,"area":null},{"id":"2306.04459","title":"Uncertainty in Natural Language Processing: Sources, Quantification, and Applications","created":"2023-06-05","cited_by_count":44,"area":null},{"id":"2204.08735","title":"Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning","created":"2022-04-19","cited_by_count":43,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"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":"2111.08456","title":"Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38,"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":"2402.12240","title":"BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2305.18764","title":"When Does Optimizing a Proper Loss Yield Calibration?","created":"2023-05-30","cited_by_count":36,"area":null},{"id":"2311.01723","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","created":"2023-11-03","cited_by_count":35,"area":"mllm"},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34,"area":null},{"id":"2207.11347","title":"An Impartial Take to the CNN vs Transformer Robustness Contest","created":"2022-07-22","cited_by_count":34,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2302.04332","title":"Continuous Learning for Android Malware Detection","created":"2023-02-08","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":"2211.11838","title":"AdaFocal: Calibration-aware Adaptive Focal Loss","created":"2022-11-21","cited_by_count":32,"area":null},{"id":"2212.02295","title":"Block Selection Method for Using Feature Norm in Out-of-distribution Detection","created":"2022-12-05","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":"2407.13588","title":"Robust Calibration of Large Vision-Language Adapters","created":"2024-07-18","cited_by_count":28,"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":"2209.07601","title":"Towards Improving Calibration in Object Detection Under Domain Shift","created":"2022-09-15","cited_by_count":26,"area":null},{"id":"2407.11682","title":"MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation","created":"2024-07-16","cited_by_count":26,"area":"distill"},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25,"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":"2212.12053","title":"On Calibrating Semantic Segmentation Models: Analyses and An Algorithm","created":"2022-12-22","cited_by_count":25,"area":null},{"id":"2305.18262","title":"Beyond Confidence: Reliable Models Should Also Consider Atypicality","created":"2023-05-29","cited_by_count":25,"area":null},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2203.01437","title":"MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks","created":"2022-03-02","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":"2206.05833","title":"COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition","created":"2022-06-12","cited_by_count":22,"area":null},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"area":null},{"id":"2104.00795","title":"No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks","created":"2021-04-01","cited_by_count":21,"area":null},{"id":"2303.02444","title":"Calibrating Transformers via Sparse Gaussian Processes","created":"2023-03-04","cited_by_count":21,"area":null},{"id":"2502.04377","title":"MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction","created":"2025-02-05","cited_by_count":21,"area":null},{"id":"2206.15400","title":"Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting","created":"2022-06-30","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":"2109.05263","title":"Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition","created":"2021-09-11","cited_by_count":19,"area":null},{"id":"2109.07258","title":"Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Setting","created":"2021-09-15","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":"2308.11990","title":"RankMixup: Ranking-Based Mixup Training for Network Calibration","created":"2023-08-23","cited_by_count":19,"area":null},{"id":"2107.04212","title":"Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation","created":"2021-07-09","cited_by_count":18,"area":null},{"id":"2202.03295","title":"Theoretical characterization of uncertainty in high-dimensional linear classification","created":"2022-02-07","cited_by_count":18,"area":null},{"id":"2212.10005","title":"Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning","created":"2022-12-20","cited_by_count":18,"area":null},{"id":"2205.05593","title":"Identifying Moments of Change from Longitudinal User Text","created":"2022-05-11","cited_by_count":17,"area":null},{"id":"2207.10130","title":"Latent Discriminant deterministic Uncertainty","created":"2022-07-20","cited_by_count":17,"area":null},{"id":"2306.01265","title":"Calibrating Multimodal Learning","created":"2023-06-02","cited_by_count":17,"area":null},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17,"area":"moe"},{"id":"2210.12760","title":"On double-descent in uncertainty quantification in overparametrized models","created":"2022-10-23","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":"2306.08271","title":"Multiclass Confidence and Localization Calibration for Object Detection","created":"2023-06-14","cited_by_count":16,"area":null},{"id":"2112.07428","title":"Obtaining Calibrated Probabilities with Personalized Ranking Models","created":"2021-12-09","cited_by_count":15,"area":null},{"id":"2304.10127","title":"Learning Sample Difficulty from Pre-trained Models for Reliable Prediction","created":"2023-04-20","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":"2312.11299","title":"Uncertainty-based Fairness Measures","created":"2023-12-18","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":"2403.10175","title":"A Short Survey on Importance Weighting for Machine Learning","created":"2024-03-15","cited_by_count":15,"area":null},{"id":"2411.03359","title":"Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection","created":"2024-11-05","cited_by_count":15,"area":"mllm"},{"id":"2111.10734","title":"Deep Probability Estimation","created":"2021-11-21","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":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2406.04370","title":"Large Language Model Confidence Estimation via Black-Box Access","created":"2024-06-01","cited_by_count":14,"area":null},{"id":"2507.00861","title":"SafeMap: Robust HD Map Construction from Incomplete Observations","created":"2025-07-01","cited_by_count":14,"area":null},{"id":"2109.10778","title":"Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images","created":"2021-09-22","cited_by_count":13,"area":null},{"id":"2112.12218","title":"Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation","created":"2021-12-22","cited_by_count":13,"area":null},{"id":"2211.15088","title":"Class Adaptive Network Calibration","created":"2022-11-28","cited_by_count":13,"area":null},{"id":"2303.02472","title":"ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure","created":"2023-03-04","cited_by_count":13,"area":null},{"id":"2307.06616","title":"SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?","created":"2023-07-13","cited_by_count":13,"area":null},{"id":"2307.12463","title":"Rethinking Data Distillation: Do Not Overlook Calibration","created":"2023-07-24","cited_by_count":13,"area":null},{"id":"2310.06549","title":"Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks","created":"2023-10-10","cited_by_count":13,"area":null},{"id":"2310.18910","title":"InstanT: Semi-supervised Learning with Instance-dependent Thresholds","created":"2023-10-29","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":"2412.06082","title":"Are foundation models for computer vision good conformal predictors?","created":"2024-12-08","cited_by_count":13,"area":"mllm"},{"id":"2210.03102","title":"Ambiguous Images With Human Judgments for Robust Visual Event Classification","created":"2022-10-06","cited_by_count":12,"area":null},{"id":"2303.06268","title":"Trust your neighbours: Penalty-based constraints for model calibration","created":"2023-03-11","cited_by_count":12,"area":null},{"id":"2303.14404","title":"Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection","created":"2023-03-25","cited_by_count":12,"area":null},{"id":"2402.04344","title":"Does confidence calibration improve conformal prediction?","created":"2024-02-06","cited_by_count":12,"area":null},{"id":"2408.02841","title":"Evaluating Posterior Probabilities: Decision Theory, Proper Scoring Rules, and Calibration","created":"2024-08-05","cited_by_count":12,"area":null},{"id":"2507.17383","title":"Confidence Calibration in Vision-Language-Action Models","created":"2025-07-23","cited_by_count":12,"area":"vla"}],"next_cursor":"100"}