{"total":186,"rows":[{"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":"2212.10957","title":"TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization","created":"2022-12-21","cited_by_count":130,"area":null},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2211.14293","title":"RbA: Segmenting Unknown Regions Rejected by All","created":"2022-11-25","cited_by_count":67,"area":null},{"id":"2101.12523","title":"Optimal strategies for reject option classifiers","created":"2021-01-29","cited_by_count":61,"area":null},{"id":"2106.15728","title":"Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles","created":"2021-06-29","cited_by_count":54,"area":null},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52,"area":null},{"id":"2111.09030","title":"Trustworthy Long-Tailed Classification","created":"2021-11-17","cited_by_count":51,"area":null},{"id":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50,"area":"lr"},{"id":"2404.18947","title":"Multimodal Fusion on Low-quality Data: A Comprehensive Survey","created":"2024-04-27","cited_by_count":49,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"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":"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":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37,"area":null},{"id":"2207.07506","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2308.07687","title":"DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Models","created":"2023-08-15","cited_by_count":26,"area":"diffusion"},{"id":"2210.05938","title":"Robust Models are less Over-Confident","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2306.08751","title":"Improving Selective Visual Question Answering by Learning from Your Peers","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2306.08328","title":"Distribution Shift Inversion for Out-of-Distribution Prediction","created":"2023-06-14","cited_by_count":23,"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":"2405.05145","title":"Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty","created":"2024-04-16","cited_by_count":20,"area":null},{"id":"2112.00337","title":"A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks","created":"2021-12-01","cited_by_count":19,"area":null},{"id":"2101.05525","title":"An evaluation of word-level confidence estimation for end-to-end automatic speech recognition","created":"2021-01-14","cited_by_count":18,"area":null},{"id":"2201.01047","title":"DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing","created":"2022-01-04","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":"2406.04802","title":"Predictive Dynamic Fusion","created":"2024-06-07","cited_by_count":17,"area":null},{"id":"2107.04517","title":"Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2110.07661","title":"Distribution-Free Federated Learning with Conformal Predictions","created":"2021-10-14","cited_by_count":16,"area":null},{"id":"2206.13202","title":"Human-AI Collaboration in Decision-Making: Beyond Learning to Defer","created":"2022-06-27","cited_by_count":16,"area":null},{"id":"2302.04002","title":"The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2406.01806","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","created":"2024-06-03","cited_by_count":16,"area":null},{"id":"2502.12802","title":"PPGF: Probability Pattern-Guided Time Series Forecasting","created":"2025-02-18","cited_by_count":16,"area":null},{"id":"2110.07922","title":"Anomaly Detection in Multi-Agent Trajectories for Automated Driving","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2208.01188","title":"Curved Geometric Networks for Visual Anomaly Recognition","created":"2022-08-02","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":"2311.00277","title":"OpenForest: A data catalogue for machine learning in forest monitoring","created":"2023-11-01","cited_by_count":15,"area":null},{"id":"2105.14785","title":"Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart","created":"2021-05-31","cited_by_count":14,"area":null},{"id":"2306.01710","title":"A Data-Driven Measure of Relative Uncertainty for Misclassification Detection","created":"2023-06-02","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":"2506.13083","title":"Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2102.12196","title":"Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis","created":"2021-02-24","cited_by_count":13,"area":null},{"id":"2106.00472","title":"Detecting Anomalies in Semantic Segmentation with Prototypes","created":"2021-06-01","cited_by_count":13,"area":null},{"id":"2106.03046","title":"Empowering Language Understanding with Counterfactual Reasoning","created":"2021-06-06","cited_by_count":13,"area":null},{"id":"2207.10851","title":"Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction","created":"2022-07-22","cited_by_count":13,"area":null},{"id":"2308.04502","title":"Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition","created":"2023-08-08","cited_by_count":13,"area":null},{"id":"2405.18902","title":"A Causal Framework for Evaluating Deferring Systems","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2110.11182","title":"SLURP: Side Learning Uncertainty for Regression Problems","created":"2021-10-21","cited_by_count":12,"area":null},{"id":"2205.14094","title":"Failure Detection in Medical Image Classification: A Reality Check and Benchmarking Testbed","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2309.01265","title":"SOAR: Scene-debiasing Open-set Action Recognition","created":"2023-09-03","cited_by_count":12,"area":null},{"id":"2402.16392","title":"Placing Objects in Context via Inpainting for Out-of-distribution Segmentation","created":"2024-02-26","cited_by_count":12,"area":null},{"id":"2405.05160","title":"Selective Classification Under Distribution Shifts","created":"2024-05-08","cited_by_count":12,"area":null},{"id":"2110.00054","title":"Learning to Predict Trustworthiness with Steep Slope Loss","created":"2021-09-30","cited_by_count":11,"area":null},{"id":"2205.12528","title":"LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2210.06788","title":"TiDAL: Learning Training Dynamics for Active Learning","created":"2022-10-13","cited_by_count":11,"area":null},{"id":"2310.01634","title":"Deep Insights into Noisy Pseudo Labeling on Graph Data","created":"2023-10-02","cited_by_count":11,"area":null},{"id":"2403.14715","title":"Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2412.03178","title":"Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation","created":"2024-12-04","cited_by_count":11,"area":null},{"id":"2505.11997","title":"Multimodal Cancer Survival Analysis via Hypergraph Learning with Cross-Modality Rebalance","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2507.08721","title":"Monitoring Risks in Test-Time Adaptation","created":"2025-07-11","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":"2206.07664","title":"CRISP - Reliable Uncertainty Estimation for Medical Image Segmentation","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2311.17105","title":"On the Calibration of Human Pose Estimation","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2403.02886","title":"Revisiting Confidence Estimation: Towards Reliable Failure Prediction","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2406.18451","title":"Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers","created":"2024-06-26","cited_by_count":10,"area":null},{"id":"2108.08748","title":"FSNet: A Failure Detection Framework for Semantic Segmentation","created":"2021-08-19","cited_by_count":9,"area":null},{"id":"2507.07620","title":"ViLU: Learning Vision-Language Uncertainties for Failure Prediction","created":"2025-07-10","cited_by_count":9,"area":"mllm"},{"id":"2306.04974","title":"Conservative Prediction via Data-Driven Confidence Minimization","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2308.12252","title":"How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy","created":"2023-08-23","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":"2503.17198","title":"Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising","created":"2025-03-21","cited_by_count":8,"area":"safety"},{"id":"2202.07825","title":"Reducing Overconfidence Predictions for Autonomous Driving Perception","created":"2022-02-16","cited_by_count":7,"area":null},{"id":"2203.12116","title":"GOSS: Towards Generalized Open-set Semantic Segmentation","created":"2022-03-23","cited_by_count":7,"area":null},{"id":"2211.16466","title":"Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation","created":"2022-11-29","cited_by_count":7,"area":null},{"id":"2308.09065","title":"Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression","created":"2023-08-17","cited_by_count":7,"area":null},{"id":"2208.11641","title":"Detecting the unknown in Object Detection","created":"2022-08-24","cited_by_count":6,"area":null},{"id":"2210.06776","title":"Improving the Reliability for Confidence Estimation","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2210.15457","title":"One-Class Risk Estimation for One-Class Hyperspectral Image Classification","created":"2022-10-27","cited_by_count":6,"area":null},{"id":"2409.18470","title":"Fairness without Sensitive Attributes via Knowledge Sharing","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2106.11641","title":"Confidence-Aware Learning for Camouflaged Object Detection","created":"2021-06-22","cited_by_count":5,"area":null},{"id":"2107.03815","title":"Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs","created":"2021-07-08","cited_by_count":5,"area":null},{"id":"2305.10384","title":"Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2307.14729","title":"Understanding Silent Failures in Medical Image Classification","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2402.08384","title":"Selective Learning: Towards Robust Calibration with Dynamic Regularization","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2103.15053","title":"Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems","created":"2021-03-28","cited_by_count":4,"area":null},{"id":"2104.04999","title":"ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms","created":"2021-04-11","cited_by_count":4,"area":null},{"id":"2302.02628","title":"Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness","created":"2023-02-06","cited_by_count":4,"area":null},{"id":"2306.16991","title":"Integrating Large Pre-trained Models into Multimodal Named Entity Recognition with Evidential Fusion","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2308.03179","title":"Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2402.05515","title":"NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2112.01360","title":"Probabilistic Approach for Road-Users Detection","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2201.12705","title":"A Robust Framework for Deep Learning Approaches to Facial Emotion Recognition and Evaluation","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2204.13347","title":"A Closer Look at Branch Classifiers of Multi-exit Architectures","created":"2022-04-28","cited_by_count":3,"area":null},{"id":"2208.06883","title":"Confidence-Guided Learning Process for Continuous Classification of Time Series","created":"2022-08-14","cited_by_count":3,"area":null},{"id":"2303.01295","title":"Iterative Assessment and Improvement of DNN Operational Accuracy","created":"2023-03-02","cited_by_count":3,"area":null},{"id":"2305.05098","title":"Who Needs Decoders? Efficient Estimation of Sequence-level Attributes","created":"2023-05-09","cited_by_count":3,"area":null}],"next_cursor":"100"}