{"total":207,"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":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264,"area":null},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121,"area":null},{"id":"2102.09692","title":"To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making","created":"2021-02-19","cited_by_count":118,"area":null},{"id":"2107.11277","title":"Machine Learning with a Reject Option: A survey","created":"2021-07-23","cited_by_count":109,"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":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75,"area":"inference"},{"id":"2202.03673","title":"Calibrated Learning to Defer with One-vs-All Classifiers","created":"2022-02-08","cited_by_count":69,"area":null},{"id":"2109.02596","title":"Scikit-dimension: a Python package for intrinsic dimension estimation","created":"2021-09-06","cited_by_count":68,"area":null},{"id":"2211.14293","title":"RbA: Segmenting Unknown Regions Rejected by All","created":"2022-11-25","cited_by_count":67,"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":"2101.12523","title":"Optimal strategies for reject option classifiers","created":"2021-01-29","cited_by_count":61,"area":null},{"id":"2210.16955","title":"Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles","created":"2022-10-30","cited_by_count":60,"area":null},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60,"area":null},{"id":"2110.06283","title":"Detecting Corrupted Labels Without Training a Model to Predict","created":"2021-10-12","cited_by_count":58,"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":"2102.08898","title":"Few-shot Conformal Prediction with Auxiliary Tasks","created":"2021-02-17","cited_by_count":53,"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":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"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":"2107.12628","title":"Energy-Based Open-World Uncertainty Modeling for Confidence Calibration","created":"2021-07-27","cited_by_count":46,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"area":null},{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2207.13048","title":"Domain Adaptation under Open Set Label Shift","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2308.13453","title":"Learning to Intervene on Concept Bottlenecks","created":"2023-08-25","cited_by_count":29,"area":null},{"id":"2401.15356","title":"A Decision Theoretic Framework for Measuring AI Reliance","created":"2024-01-27","cited_by_count":28,"area":null},{"id":"2201.02331","title":"iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection","created":"2022-01-07","cited_by_count":27,"area":null},{"id":"2403.02683","title":"Learning to Defer to a Population: A Meta-Learning Approach","created":"2024-03-05","cited_by_count":27,"area":null},{"id":"2106.00461","title":"To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods","created":"2021-06-01","cited_by_count":26,"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":"2106.09119","title":"Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL","created":"2021-06-16","cited_by_count":24,"area":"offlinerl"},{"id":"2306.08328","title":"Distribution Shift Inversion for Out-of-Distribution Prediction","created":"2023-06-14","cited_by_count":23,"area":null},{"id":"2110.14019","title":"Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection","created":"2021-10-26","cited_by_count":21,"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":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2306.04590","title":"Proximity-Informed Calibration for Deep Neural Networks","created":"2023-06-07","cited_by_count":18,"area":null},{"id":"2107.09734","title":"Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions","created":"2021-07-20","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":"2306.06849","title":"Mitigating Transformer Overconfidence via Lipschitz Regularization","created":"2023-06-12","cited_by_count":15,"area":null},{"id":"2402.04655","title":"Open-Vocabulary Calibration for Fine-tuned CLIP","created":"2024-02-07","cited_by_count":15,"area":"mllm"},{"id":"2204.05030","title":"Assessing the communication gap between AI models and healthcare professionals: explainability, utility and trust in AI-driven clinical decision-making","created":"2022-04-11","cited_by_count":14,"area":null},{"id":"2302.02924","title":"Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural Networks","created":"2023-02-06","cited_by_count":14,"area":null},{"id":"2404.12667","title":"Detecting Out-Of-Distribution Earth Observation Images with Diffusion Models","created":"2024-04-19","cited_by_count":14,"area":"diffusion"},{"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":"2109.09658","title":"FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging","created":"2021-09-20","cited_by_count":13,"area":null},{"id":"2305.00550","title":"SoK: Pragmatic Assessment of Machine Learning for Network Intrusion Detection","created":"2023-04-30","cited_by_count":13,"area":null},{"id":"2107.14000","title":"Resisting Out-of-Distribution Data Problem in Perturbation of XAI","created":"2021-07-27","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":"2312.12703","title":"Federated Learning with Extremely Noisy Clients via Negative Distillation","created":"2023-12-20","cited_by_count":12,"area":"distill"},{"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":"2409.06424","title":"A Likelihood Ratio-Based Approach to Segmenting Unknown Objects","created":"2024-09-10","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":"2305.01481","title":"Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2309.10852","title":"Using AI Uncertainty Quantification to Improve Human Decision-Making","created":"2023-09-19","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":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","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":"2103.12628","title":"Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs","created":"2021-03-23","cited_by_count":9,"area":null},{"id":"2106.08365","title":"Test Sample Accuracy Scales with Training Sample Density in Neural Networks","created":"2021-06-15","cited_by_count":9,"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":"2112.06384","title":"WOOD: Wasserstein-based Out-of-Distribution Detection","created":"2021-12-13","cited_by_count":9,"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":"2204.05941","title":"Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search","created":"2022-04-12","cited_by_count":9,"area":null},{"id":"2112.03270","title":"Toward a Taxonomy of Trust for Probabilistic Machine Learning","created":"2021-12-05","cited_by_count":8,"area":null},{"id":"2206.08288","title":"Balancing Cost and Quality: An Exploration of Human-in-the-loop Frameworks for Automated Short Answer Scoring","created":"2022-06-16","cited_by_count":8,"area":null},{"id":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2102.05140","title":"Locally Adaptive Label Smoothing for Predictive Churn","created":"2021-02-09","cited_by_count":7,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2203.08491","title":"Deepchecks: A Library for Testing and Validating Machine Learning Models and Data","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2205.09817","title":"MiDAS: Multi-integrated Domain Adaptive Supervision for Fake News Detection","created":"2022-05-19","cited_by_count":7,"area":null},{"id":"2210.06789","title":"Large-Scale Open-Set Classification Protocols for ImageNet","created":"2022-10-13","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":"2312.09454","title":"Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review","created":"2023-11-15","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":"2104.14435","title":"Customizable Reference Runtime Monitoring of Neural Networks using Resolution Boxes","created":"2021-04-25","cited_by_count":6,"area":null},{"id":"2210.05508","title":"Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data","created":"2022-10-11","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":"2405.12081","title":"Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2409.12805","title":"Robust estimation of the intrinsic dimension of data sets with quantum cognition machine learning","created":"2024-09-19","cited_by_count":6,"area":null},{"id":"2501.02767","title":"Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training","created":"2025-01-06","cited_by_count":6,"area":null},{"id":"2104.06982","title":"To Trust or Not to Trust a Regressor: Estimating and Explaining Trustworthiness of Regression Predictions","created":"2021-04-14","cited_by_count":5,"area":null},{"id":"2107.02990","title":"Test for non-negligible adverse shifts","created":"2021-07-07","cited_by_count":5,"area":null},{"id":"2201.09815","title":"Analytic Mutual Information in Bayesian Neural Networks","created":"2022-01-24","cited_by_count":5,"area":null},{"id":"2403.00980","title":"Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides?","created":"2024-03-01","cited_by_count":5,"area":null},{"id":"2505.15008","title":"Know When to Abstain: Optimal Selective Classification with Likelihood Ratios","created":"2025-05-21","cited_by_count":5,"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":"2105.01195","title":"Quality Assurance Challenges for Machine Learning Software Applications During Software Development Life Cycle Phases","created":"2021-05-03","cited_by_count":4,"area":null},{"id":"2110.03092","title":"A Uniform Framework for Anomaly Detection in Deep Neural Networks","created":"2021-10-06","cited_by_count":4,"area":null},{"id":"2203.00214","title":"Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data","created":"2022-03-01","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":"2304.08288","title":"Toward Auto-evaluation with Confidence-based Category Relation-aware Regression","created":"2023-04-17","cited_by_count":4,"area":null},{"id":"2402.15572","title":"Improving Explainable Object-induced Model through Uncertainty for Automated Vehicles","created":"2024-02-23","cited_by_count":4,"area":null}],"next_cursor":"100"}