{"total":286,"rows":[{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2304.11633","title":"Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness","created":"2023-04-23","cited_by_count":130,"area":null},{"id":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2103.03323","title":"Distribution-free uncertainty quantification for classification under label shift","created":"2021-03-04","cited_by_count":101,"area":null},{"id":"2108.00106","title":"Soft Calibration Objectives for Neural Networks","created":"2021-07-30","cited_by_count":92,"area":null},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79,"area":null},{"id":"2112.10327","title":"Classifier Calibration: A survey on how to assess and improve predicted class probabilities","created":"2021-12-20","cited_by_count":73,"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":"2205.05878","title":"Training Uncertainty-Aware Classifiers with Conformalized Deep Learning","created":"2022-05-12","cited_by_count":64,"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":"2302.01790","title":"Understanding metric-related pitfalls in image analysis validation","created":"2023-02-03","cited_by_count":58,"area":null},{"id":"2211.16886","title":"A Unifying Theory of Distance from Calibration","created":"2022-11-30","cited_by_count":53,"area":null},{"id":"2406.19272","title":"Stochastic Concept Bottleneck Models","created":"2024-06-27","cited_by_count":51,"area":null},{"id":"2111.09277","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","created":"2021-11-17","cited_by_count":49,"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":"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":"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":"2105.04656","title":"Distribution-free calibration guarantees for histogram binning without sample splitting","created":"2021-05-10","cited_by_count":45,"area":null},{"id":"2106.09848","title":"PAC Prediction Sets Under Covariate Shift","created":"2021-06-17","cited_by_count":45,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"area":null},{"id":"2103.15718","title":"von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning","created":"2021-03-29","cited_by_count":42,"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":"2109.14591","title":"Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration","created":"2021-09-29","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":"2101.05036","title":"Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors","created":"2021-01-13","cited_by_count":37,"area":null},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34,"area":null},{"id":"2105.04290","title":"Meta-Cal: Well-controlled Post-hoc Calibration by Ranking","created":"2021-05-10","cited_by_count":33,"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":"2205.09680","title":"Metrics of calibration for probabilistic predictions","created":"2022-05-19","cited_by_count":32,"area":null},{"id":"2210.16315","title":"Beyond calibration: estimating the grouping loss of modern neural networks","created":"2022-10-28","cited_by_count":32,"area":null},{"id":"2211.11838","title":"AdaFocal: Calibration-aware Adaptive Focal Loss","created":"2022-11-21","cited_by_count":32,"area":null},{"id":"2401.16646","title":"Incoherent Probability Judgments in Large Language Models","created":"2024-01-30","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":"2202.07650","title":"Conformal Prediction Sets with Limited False Positives","created":"2022-02-15","cited_by_count":28,"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":"2208.00461","title":"Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks","created":"2022-07-31","cited_by_count":24,"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":"2308.12963","title":"MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models","created":"2023-08-24","cited_by_count":21,"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":"2402.08733","title":"Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2210.01964","title":"The Calibration Generalization Gap","created":"2022-10-05","cited_by_count":18,"area":null},{"id":"2501.19195","title":"Rethinking Early Stopping: Refine, Then Calibrate","created":"2025-01-31","cited_by_count":17,"area":null},{"id":"2312.02592","title":"FRAPPE: A Group Fairness Framework for Post-Processing Everything","created":"2023-12-05","cited_by_count":16,"area":null},{"id":"2208.12606","title":"Pushing the limits of fairness impossibility: Who's the fairest of them all?","created":"2022-08-24","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":"2101.06829","title":"Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models","created":"2021-01-18","cited_by_count":14,"area":null},{"id":"2402.06625","title":"Understanding the Effects of Iterative Prompting on Truthfulness","created":"2024-02-09","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":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2410.06615","title":"QA-Calibration of Language Model Confidence Scores","created":"2024-10-09","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},{"id":"2304.06537","title":"Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution","created":"2023-04-13","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":"2502.19851","title":"Can a calibration metric be both testable and actionable?","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2101.05397","title":"Should Ensemble Members Be Calibrated?","created":"2021-01-13","cited_by_count":11,"area":null},{"id":"2112.12560","title":"On the relationship between calibrated predictors and unbiased volume estimation","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2202.04348","title":"MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration","created":"2022-02-09","cited_by_count":11,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2308.11838","title":"A Benchmark Study on Calibration","created":"2023-08-23","cited_by_count":11,"area":null},{"id":"2312.08589","title":"Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors","created":"2023-12-14","cited_by_count":11,"area":null},{"id":"2405.20459","title":"On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines","created":"2024-05-30","cited_by_count":11,"area":null},{"id":"2411.02988","title":"Confidence Calibration of Classifiers with Many Classes","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2103.03945","title":"SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Models","created":"2021-03-05","cited_by_count":10,"area":null},{"id":"2106.05515","title":"Understanding the Under-Coverage Bias in Uncertainty Estimation","created":"2021-06-10","cited_by_count":10,"area":null},{"id":"2206.04287","title":"Evaluating Aleatoric Uncertainty via Conditional Generative Models","created":"2022-06-09","cited_by_count":10,"area":null},{"id":"2305.10886","title":"Minimum-Risk Recalibration of Classifiers","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2306.04985","title":"Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping","created":"2023-06-08","cited_by_count":10,"area":null},{"id":"2308.03003","title":"Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error","created":"2023-08-06","cited_by_count":10,"area":null},{"id":"2402.13187","title":"Testing Calibration in Nearly-Linear Time","created":"2024-02-20","cited_by_count":10,"area":null},{"id":"2405.15709","title":"Information-theoretic Generalization Analysis for Expected Calibration Error","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2406.00332","title":"A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning","created":"2024-06-01","cited_by_count":10,"area":null},{"id":"2202.07679","title":"Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2206.01570","title":"On Calibration of Graph Neural Networks for Node Classification","created":"2022-06-03","cited_by_count":9,"area":null},{"id":"2207.01242","title":"Parametric and Multivariate Uncertainty Calibration for Regression and Object Detection","created":"2022-07-04","cited_by_count":9,"area":null},{"id":"2302.06245","title":"Calibrating a Deep Neural Network with Its Predecessors","created":"2023-02-13","cited_by_count":9,"area":null},{"id":"2305.14765","title":"Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2305.14802","title":"Estimating Large Language Model Capabilities without Labeled Test Data","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2312.06645","title":"Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection","created":"2023-12-11","cited_by_count":9,"area":null},{"id":"2403.18286","title":"Few-Shot Recalibration of Language Models","created":"2024-03-27","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2101.02971","title":"From Black-box to White-box: Examining Confidence Calibration under different Conditions","created":"2021-01-08","cited_by_count":8,"area":null},{"id":"2111.03135","title":"Scaffolding Sets","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2205.07295","title":"Posterior Probability Matters: Doubly-Adaptive Calibration for Neural Predictions in Online Advertising","created":"2022-05-15","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":"2401.03350","title":"Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks","created":"2024-01-07","cited_by_count":8,"area":null},{"id":"2406.04068","title":"Reassessing How to Compare and Improve the Calibration of Machine Learning Models","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2407.08649","title":"Confidence-based Estimators for Predictive Performance in Model Monitoring","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2110.15231","title":"Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data","created":"2021-10-28","cited_by_count":7,"area":null},{"id":"2202.12412","title":"Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration","created":"2022-02-24","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":"2401.02718","title":"Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence","created":"2024-01-05","cited_by_count":7,"area":null}],"next_cursor":"100"}