{"total":58,"rows":[{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"area":null},{"id":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83,"area":null},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65,"area":null},{"id":"2505.24785","title":"EXP-Bench: Can AI Conduct AI Research Experiments?","created":"2025-05-30","cited_by_count":37,"area":null},{"id":"2406.10881","title":"Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals","created":"2024-06-16","cited_by_count":32,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2406.06487","title":"When is Multicalibration Post-Processing Necessary?","created":"2024-06-10","cited_by_count":18,"area":null},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","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":"2311.11837","title":"Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms","created":"2023-11-20","cited_by_count":14,"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":"2510.04013","title":"LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2402.13187","title":"Testing Calibration in Nearly-Linear Time","created":"2024-02-20","cited_by_count":10,"area":null},{"id":"2504.15582","title":"Smooth Calibration and Decision Making","created":"2025-04-22","cited_by_count":10,"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":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2502.20375","title":"When does a predictor know its own loss?","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2505.17435","title":"Discretization-free Multicalibration through Loss Minimization over Tree Ensembles","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2403.11964","title":"Probabilistic Calibration by Design for Neural Network Regression","created":"2024-03-18","cited_by_count":6,"area":null},{"id":"2605.27752","title":"Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2509.19884","title":"MCGrad: Multicalibration at Web Scale","created":"2025-09-24","cited_by_count":5,"area":null},{"id":"2605.01428","title":"Hallucinations Undermine Trust; Metacognition is a Way Forward","created":"2026-05-02","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":"2509.02279","title":"Calibration through the Lens of Indistinguishability","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2506.23492","title":"Sample Margin-Aware Recalibration of Temperature Scaling","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2511.13699","title":"Efficient Calibration for Decision Making","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2601.08064","title":"Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2603.16015","title":"The Importance of Being Smoothly Calibrated","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2506.17035","title":"Critical Appraisal of Fairness Metrics in Clinical Predictive AI","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2605.30188","title":"CalArena: A Large-Scale Post-Hoc Calibration Benchmark","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.20526","title":"ConfidenceBench: Evaluating Confidence Calibration in Large Language Models","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2406.00529","title":"On the Use of Anchoring for Training Vision Models","created":"2024-06-01","cited_by_count":1,"area":null},{"id":"2412.10658","title":"Combining Priors with Experience: Confidence Calibration Based on Binomial Process Modeling","created":"2024-12-14","cited_by_count":1,"area":null},{"id":"2506.10572","title":"Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2511.00301","title":"A systematic evaluation of uncertainty quantification techniques in deep learning: a case study in photoplethysmography signal analysis","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2604.05397","title":"Confidence Should Be Calibrated More Than One Turn Deep","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.09850","title":"Probing Routing-Conditional Calibration in Attention-Residual Transformers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.07822","title":"The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2610.02293","title":"HakemBench: A Turkish Benchmark of Typed Decisions","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2503.01195","title":"PostHoc FREE Calibrating on Kolmogorov Arnold Networks","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2508.08547","title":"Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2509.16930","title":"Auditability and the Landscape of Distance to Multicalibration","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2510.01987","title":"Private Federated Multiclass Post-hoc Calibration","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2604.12491","title":"Calibrated Confidence Estimation for Tabular Question Answering","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.04231","title":"Anatomy of a failure: When, how, and why deep vision fails in scientific domains","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.07808","title":"The Minimax Rate of Perturbed Second-Order Calibration","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.13484","title":"Discovery of Hidden Miscalibration Regimes","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.23017","title":"Smoothed Elicitation Complexity for Approximate $\\Gamma$-calibration of Discrete Classification Tasks","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.29925","title":"Bandwidth Selection in Kernel Density Estimation for Model Calibration","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.01072","title":"Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.25388","title":"PICPIs: Prediction-Interval-Conditional Prediction Intervals","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.38797","title":"Evaluating Persistent Calibration under Evolving Model Knowledge","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.38936","title":"Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation Budgets","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01006","title":"Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01495","title":"Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06744","title":"ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17016","title":"ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17096","title":"Towards Universal Calibration for In-Context Classification","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}