{"total":92,"rows":[{"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":"2412.12472","title":"Knowledge Boundary of Large Language Models: A Survey","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2406.18814","title":"Length Optimization in Conformal Prediction","created":"2024-06-27","cited_by_count":39,"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":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2505.19970","title":"CP-Router: An Uncertainty-Aware Router Between LLM and LRM","created":"2025-05-26","cited_by_count":20,"area":"lr"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2410.08174","title":"Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models","created":"2024-10-10","cited_by_count":19,"area":"mllm"},{"id":"2501.00555","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","created":"2024-12-31","cited_by_count":18,"area":null},{"id":"2512.03109","title":"E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing","created":"2025-12-02","cited_by_count":17,"area":"lr"},{"id":"2505.13732","title":"Backward Conformal Prediction","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2505.17126","title":"Conformal Language Model Reasoning with Coherent Factuality","created":"2025-05-21","cited_by_count":14,"area":"lr"},{"id":"2407.21057","title":"Multi-group Uncertainty Quantification for Long-form Text Generation","created":"2024-07-25","cited_by_count":13,"area":null},{"id":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2411.01696","title":"Conformal Risk Minimization with Variance Reduction","created":"2024-11-03","cited_by_count":11,"area":null},{"id":"2410.01660","title":"Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2503.10512","title":"Conformal Prediction Sets for Deep Generative Models via Reduction to Conformal Regression","created":"2025-03-13","cited_by_count":10,"area":null},{"id":"2505.08784","title":"PCS-UQ: Uncertainty Quantification via the Predictability-Computability-Stability Framework","created":"2025-05-13","cited_by_count":9,"area":null},{"id":"2508.15842","title":"Lexical Hints of Accuracy in LLM Reasoning Chains","created":"2025-08-19","cited_by_count":9,"area":"lr"},{"id":"2502.20285","title":"Conformal Tail Risk Control for Large Language Model Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2506.20978","title":"Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality","created":"2025-06-26","cited_by_count":8,"area":"rag"},{"id":"2410.09408","title":"C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Sets","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2503.10345","title":"Mirror Online Conformal Prediction with Intermittent Feedback","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2507.03279","title":"Conformal Information Pursuit for Interactively Guiding Large Language Models","created":"2025-07-04","cited_by_count":7,"area":null},{"id":"2510.23476","title":"Human-AI Collaborative Uncertainty Quantification","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2604.09155","title":"CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation","created":"2026-04-10","cited_by_count":7,"area":"agents"},{"id":"2506.05497","title":"Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2509.20461","title":"Document Summarization with Conformal Importance Guarantees","created":"2025-09-24","cited_by_count":6,"area":null},{"id":"2510.05566","title":"Domain-Shift-Aware Conformal Prediction for Large Language Models","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2603.02196","title":"Conformal Policy Control","created":"2026-03-02","cited_by_count":6,"area":null},{"id":"2409.01236","title":"Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2501.18363","title":"Exploring the Noise Robustness of Online Conformal Prediction","created":"2025-01-30","cited_by_count":5,"area":null},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2509.02844","title":"Conformal Prediction for Time-series Forecasting with Change Points","created":"2025-09-02","cited_by_count":5,"area":null},{"id":"2510.04318","title":"Adaptive Coverage Policies in Conformal Prediction","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2409.16829","title":"Conditional Testing based on Localized Conformal p-values","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2502.14268","title":"MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2510.08075","title":"Multi-Condition Conformal Selection","created":"2025-10-09","cited_by_count":4,"area":"alignment"},{"id":"2511.13240","title":"Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions","created":"2025-11-17","cited_by_count":4,"area":"agents"},{"id":"2604.01170","title":"Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning","created":"2026-04-01","cited_by_count":4,"area":"lr"},{"id":"2604.17984","title":"Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization","created":"2026-04-20","cited_by_count":4,"area":null},{"id":"2606.29054","title":"When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation","created":"2026-06-27","cited_by_count":4,"area":null},{"id":"2607.06503","title":"Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2506.13593","title":"Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2601.15296","title":"Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration","created":"2026-01-02","cited_by_count":3,"area":"lr"},{"id":"2604.19444","title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","created":"2026-04-21","cited_by_count":3,"area":"lr"},{"id":"2503.14754","title":"Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2508.04915","title":"ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2509.23002","title":"Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty","created":"2025-09-26","cited_by_count":2,"area":"synth"},{"id":"2510.25770","title":"E-Scores for (In)Correctness Assessment of Generative Model Outputs","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2602.07633","title":"Flow-Based Conformal Predictive Distributions","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2605.10974","title":"Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.30085","title":"Conformal Certification of Reasoning Trace Prefixes","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.01850","title":"Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2501.01963","title":"Statistical learning does not always entail knowledge","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2502.20560","title":"Towards Statistical Factuality Guarantee for Large Vision-Language Models","created":"2025-02-27","cited_by_count":1,"area":"mllm"},{"id":"2504.03640","title":"Bonsai: Interpretable Tree-Adaptive Grounded Reasoning","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2505.21147","title":"Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Score","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2509.01455","title":"Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2511.16845","title":"Provably Minimum-Length Conformal Prediction Sets for Ordinal Classification","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2602.01285","title":"Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.01733","title":"Improving Backward Conformal Prediction via Non-Conformity Score Transformation","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.23923","title":"Elements of Conformal Prediction","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.13991","title":"Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.16217","title":"Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2605.14098","title":"Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.30641","title":"COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.03731","title":"Conformal Language Modeling via Posterior Sampling","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.12587","title":"Strategic Decision Support for AI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.15841","title":"Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2606.31600","title":"On Optimal Data Splitting for Split Conformal Prediction","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.01460","title":"Conformalized Large Language Models under Configuration Shift","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.05439","title":"SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2508.14118","title":"Hallucinations in medical devices","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2511.06575","title":"CoFineLLM: Conformal Finetuning of LLMs for Language-Instructed Robot Planning","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2602.07530","title":"Compact Conformal Subgraphs","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.19498","title":"Softmax is not Enough (for Adaptive Conformal Classification)","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.00105","title":"LIDS: LLM Summary Inference Under the Layered Lens","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.14422","title":"MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2607.16704","title":"Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2607.25018","title":"Conformal Cascade: Distribution-Free Accuracy Guarantees for Multi-Tier LLM Inference","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.27847","title":"From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosis","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.29789","title":"A Unified Perspective on Conformal Prediction and Wasserstein Distributionally Robust Optimization for Uncertainty Quantification","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.01375","title":"IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2609.03005","title":"Unifying Conformal Language Tasks with In-Context Ensembles","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.17882","title":"Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.36689","title":"CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04239","title":"Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}