{"total":99,"rows":[{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2407.18370","title":"Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement","created":"2024-07-25","cited_by_count":105,"area":null},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92,"area":null},{"id":"2404.15993","title":"Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach","created":"2024-04-24","cited_by_count":76,"area":null},{"id":"2407.00499","title":"ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees","created":"2024-06-29","cited_by_count":65,"area":null},{"id":"2403.11903","title":"A Closer Look at Claim Decomposition","created":"2024-03-18","cited_by_count":41,"area":null},{"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":"2410.06494","title":"Conformal Prediction: A Data Perspective","created":"2024-10-09","cited_by_count":25,"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":"2501.00555","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","created":"2024-12-31","cited_by_count":18,"area":null},{"id":"2505.23912","title":"LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations","created":"2025-05-29","cited_by_count":17,"area":null},{"id":"2406.05213","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2407.03572","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","created":"2024-07-04","cited_by_count":16,"area":null},{"id":"2410.01888","title":"Conformal Prediction Sets Can Cause Disparate Impact","created":"2024-10-02","cited_by_count":14,"area":null},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"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":"2405.03164","title":"The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning","created":"2024-05-06","cited_by_count":11,"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":"2410.06296","title":"Conformal Structured Prediction","created":"2024-10-08","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":"2506.10060","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2605.20270","title":"Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs","created":"2026-05-18","cited_by_count":8,"area":null},{"id":"2411.02603","title":"FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees","created":"2024-11-04","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":"2603.21172","title":"Entropy Alone is Insufficient for Safe Selective Prediction in LLMs","created":"2026-03-22","cited_by_count":7,"area":null},{"id":"2405.13022","title":"LLMs can learn self-restraint through iterative self-reflection","created":"2024-05-15","cited_by_count":6,"area":null},{"id":"2406.01416","title":"Adapting Prediction Sets to Distribution Shifts Without Labels","created":"2024-06-03","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":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2505.23804","title":"Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2604.27914","title":"Geometry-Calibrated Conformal Abstention for Language Models","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2607.08456","title":"Two Axes of LLM Abstention: Answer Correctness and Question Answerability","created":"2026-07-09","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":"2501.14544","title":"Distributed Conformal Prediction via Message Passing","created":"2025-01-24","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":"2504.12589","title":"Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2506.05434","title":"Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2509.07054","title":"Statistical Methods in Generative AI","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2603.22966","title":"Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees","created":"2026-03-24","cited_by_count":4,"area":null},{"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":"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":"2507.06489","title":"On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks","created":"2025-07-09","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":"2503.14754","title":"Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2506.04051","title":"High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2509.15356","title":"Predicting Language Models' Success at Zero-Shot Probabilistic Prediction","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2509.24095","title":"Singleton-Optimized Conformal Prediction","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.13103","title":"ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models","created":"2025-10-15","cited_by_count":2,"area":null},{"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":"2606.08969","title":"CARE: A Conformal Safety Layer for Medical Summarization","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2608.23244","title":"Credal Large Language Models for Semantic Commitment under Uncertainty","created":"2026-08-24","cited_by_count":2,"area":null},{"id":"2504.03640","title":"Bonsai: Interpretable Tree-Adaptive Grounded Reasoning","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2505.13553","title":"Towards Functional Correctness of Large Code Models with Selective Generation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.18425","title":"Advertising in AI systems: Society must be vigilant","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2508.07095","title":"Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust","created":"2025-08-09","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":"2602.01285","title":"Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses","created":"2026-02-01","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":"2604.15109","title":"IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.15416","title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.21748","title":"RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.28920","title":"Conf-Gen: Conformal Uncertainty Quantification for Generative Models","created":"2026-05-27","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":"2606.15153","title":"False Sense of Safety in Selective Signal Classification: Auditing Bound Tightness and Exchangeability for Risk Control","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2607.04430","title":"Uncertainty-Aware Abstention in Large Language Models with Provable Alignment Guarantees","created":"2026-07-05","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":"2608.25824","title":"Localize-Then-Decide Guarantees for LLM Judgments","created":"2026-08-26","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":"2510.03527","title":"Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2602.00848","title":"Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.01912","title":"Reliable Real-Time Value at Risk Estimation via Quantile Regression Forest with Conformal Calibration","created":"2026-02-02","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":"2604.23987","title":"Continual Calibration: Coverage Can Collapse Before Accuracy in Lifelong LLM Fine-Tuning","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.04638","title":"Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.07570","title":"Can LLMs extract scientific consensus? A case study in high-temperature superconductivity","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.02510","title":"Online Safety Monitoring for LLMs","created":"2026-07-02","cited_by_count":0,"area":null},{"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":"2608.14639","title":"Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.23744","title":"Calibration-Preserving Pruning: Compression as a Reliability Contract","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.00838","title":"Probabilistic Model Checking of Autoregressive Neural Sequence Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03005","title":"Unifying Conformal Language Tasks with In-Context Ensembles","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04445","title":"Conformity Breaks Conformal Prediction","created":"2026-09-03","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":"2609.23239","title":"SoK: Formal Methods for Fact-Checking and Information Integrity","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.25938","title":"Certified Against Which Oracle? Execution Labels Set the Reported Risk of Conformal Abstention for Text-to-SQL","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.00212","title":"EviGraph: Proof-Carrying Selective Recommendation over Temporal Public-Service Knowledge Graphs","created":"2026-09-21","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},{"id":"2610.06974","title":"Uncertainty in Representation Learning on Knowledge Graphs","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}