{"total":29,"rows":[{"id":"2402.19460","title":"Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks","created":"2024-02-29","cited_by_count":78,"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":"2307.03810","title":"URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates","created":"2023-07-07","cited_by_count":17,"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":"2410.15361","title":"A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators","created":"2024-10-20","cited_by_count":15,"area":null},{"id":"2406.03323","title":"Comparative Benchmarking of Failure Detection Methods in Medical Image Segmentation: Unveiling the Role of Confidence Aggregation","created":"2024-06-05","cited_by_count":12,"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":"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":"2411.02988","title":"Confidence Calibration of Classifiers with Many Classes","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2402.16569","title":"Pretrained Visual Uncertainties","created":"2024-02-26","cited_by_count":10,"area":null},{"id":"2304.04906","title":"Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2405.11533","title":"Hierarchical Selective Classification","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2411.01981","title":"Typicalness-Aware Learning for Failure Detection","created":"2024-11-04","cited_by_count":6,"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":"2407.02062","title":"Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2505.18636","title":"Asymmetric Duos: Sidekicks Improve Uncertainty","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2509.16696","title":"Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2407.02138","title":"Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2408.14281","title":"Uncertainties of Latent Representations in Computer Vision","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2410.23046","title":"Legitimate ground-truth-free metrics for deep uncertainty classification scoring","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2505.22843","title":"On the Reliability and Stability of Selective Methods in Malware Classification Tasks","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2505.23463","title":"Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss","created":"2025-05-29","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":"2605.01346","title":"CHASE: Competing Hypotheses for Ambiguity-Aware Selective Prediction","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2607.12273","title":"Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.14617","title":"Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.17386","title":"Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.35910","title":"The Decision Value of Perception Compute","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}