{"total":76,"rows":[{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856,"area":"lr"},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783,"area":"lr"},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131,"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":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72,"area":null},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69,"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":"2206.15474","title":"Forecasting Future World Events with Neural Networks","created":"2022-06-30","cited_by_count":63,"area":null},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47,"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":"2101.06536","title":"Deep Cox Mixtures for Survival Regression","created":"2021-01-16","cited_by_count":44,"area":null},{"id":"2310.19208","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","created":"2023-10-30","cited_by_count":44,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2101.00345","title":"Modeling Fine-Grained Entity Types with Box Embeddings","created":"2021-01-02","cited_by_count":36,"area":null},{"id":"2112.07184","title":"Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation","created":"2021-12-14","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":"2104.08676","title":"Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning","created":"2021-04-18","cited_by_count":31,"area":null},{"id":"2203.07559","title":"On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency","created":"2022-03-14","cited_by_count":31,"area":null},{"id":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2201.12078","title":"You Only Cut Once: Boosting Data Augmentation with a Single Cut","created":"2022-01-28","cited_by_count":22,"area":null},{"id":"2211.08701","title":"Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction","created":"2022-11-16","cited_by_count":22,"area":null},{"id":"2212.00720","title":"A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks","created":"2022-11-16","cited_by_count":22,"area":null},{"id":"2402.07417","title":"An Empirical Study Into What Matters for Calibrating Vision-Language Models","created":"2024-02-12","cited_by_count":20,"area":"mllm"},{"id":"2203.02586","title":"Concept-based Explanations for Out-Of-Distribution Detectors","created":"2022-03-04","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":"2402.13213","title":"Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A","created":"2024-02-20","cited_by_count":16,"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":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2308.04635","title":"Where's the Liability in Harmful AI Speech?","created":"2023-08-09","cited_by_count":12,"area":"safety"},{"id":"2101.05397","title":"Should Ensemble Members Be Calibrated?","created":"2021-01-13","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":"2112.04620","title":"Online Calibrated and Conformal Prediction Improves Bayesian Optimization","created":"2021-12-08","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":"2205.15955","title":"CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping","created":"2022-05-31","cited_by_count":8,"area":null},{"id":"2506.03616","title":"Learning to Insert [PAUSE] Tokens for Better Reasoning","created":"2025-06-04","cited_by_count":8,"area":"lr"},{"id":"2410.04315","title":"Calibrating Expressions of Certainty","created":"2024-10-06","cited_by_count":7,"area":null},{"id":"2102.06859","title":"Capturing Label Distribution: A Case Study in NLI","created":"2021-02-13","cited_by_count":6,"area":null},{"id":"2205.10586","title":"Calibration of Natural Language Understanding Models with Venn--ABERS Predictors","created":"2022-05-21","cited_by_count":6,"area":null},{"id":"2310.17159","title":"MaxEnt Loss: Constrained Maximum Entropy for Calibration under Out-of-Distribution Shift","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2211.07625","title":"What Images are More Memorable to Machines?","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2309.13132","title":"Understanding Calibration of Deep Neural Networks for Medical Image Classification","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2405.13922","title":"Towards Certification of Uncertainty Calibration under Adversarial Attacks","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2502.19684","title":"GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2503.22725","title":"Uncertainty Weighted Gradients for Model Calibration","created":"2025-03-26","cited_by_count":5,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2307.13539","title":"Model Calibration in Dense Classification with Adaptive Label Perturbation","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2311.12800","title":"Understanding Data Augmentation from a Robustness Perspective","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2504.10007","title":"Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2203.09278","title":"Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2203.11413","title":"Learning Confidence for Transformer-based Neural Machine Translation","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2205.09809","title":"Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems","created":"2022-05-19","cited_by_count":2,"area":null},{"id":"2312.08586","title":"Estimating calibration error under label shift without labels","created":"2023-12-14","cited_by_count":2,"area":null},{"id":"2312.15086","title":"HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings","created":"2023-12-22","cited_by_count":2,"area":null},{"id":"2502.15131","title":"Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2506.17968","title":"h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2606.30814","title":"When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2109.07494","title":"Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets","created":"2021-09-15","cited_by_count":1,"area":null},{"id":"2305.19498","title":"Perception and Semantic Aware Regularization for Sequential Confidence Calibration","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2405.02830","title":"You Only Need Half: Boosting Data Augmentation by Using Partial Content","created":"2024-05-05","cited_by_count":1,"area":null},{"id":"2505.24147","title":"Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2508.09116","title":"Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.13539","title":"Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2205.12507","title":"Re-Examining Calibration: The Case of Question Answering","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2212.04059","title":"MixBoost: Improving the Robustness of Deep Neural Networks by Boosting Data Augmentation","created":"2022-12-08","cited_by_count":0,"area":null},{"id":"2302.12367","title":"Extracting Victim Counts from Text","created":"2023-02-23","cited_by_count":0,"area":null},{"id":"2304.13883","title":"Neural Keyphrase Generation: Analysis and Evaluation","created":"2023-04-27","cited_by_count":0,"area":null},{"id":"2409.00980","title":"DNN-GDITD: Out-of-distribution detection via Deep Neural Network based Gaussian Descriptor for Imbalanced Tabular Data","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2409.04241","title":"Calibration of Network Confidence for Unsupervised Domain Adaptation Using Estimated Accuracy","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2501.04861","title":"LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2505.19396","title":"Uniform convergence of the smooth calibration error and its relationship with functional gradient","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2510.19328","title":"Clustered Calibration: Representation-Aware Probability Calibration via Learned Subpopulations","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2604.12245","title":"Socrates Loss: Unifying Confidence Calibration and Classification by Leveraging the Unknown","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2608.12100","title":"Confidence Calibration of Deep Learning Systems","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}