{"total":131,"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":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54,"area":"alignment"},{"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":"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":"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":"2512.03109","title":"E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing","created":"2025-12-02","cited_by_count":17,"area":"lr"},{"id":"2602.16699","title":"Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents","created":"2026-02-18","cited_by_count":17,"area":"agents"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"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":"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":"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":"2405.18780","title":"Certifying Counterfactual Bias in LLMs","created":"2024-05-29","cited_by_count":10,"area":"safety"},{"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":"2502.20285","title":"Conformal Tail Risk Control for Large Language Model Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2506.10060","title":"Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2604.25235","title":"VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation","created":"2026-04-28","cited_by_count":8,"area":"mllm"},{"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":"2604.01413","title":"Adaptive Stopping for Multi-Turn LLM Reasoning","created":"2026-04-01","cited_by_count":7,"area":"lr"},{"id":"2605.18812","title":"PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines","created":"2026-05-12","cited_by_count":7,"area":"rag"},{"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":"2604.01170","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":"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":"2509.25459","title":"SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA","created":"2025-09-29","cited_by_count":3,"area":"rag"},{"id":"2601.15296","title":"Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration","created":"2026-01-02","cited_by_count":3,"area":"lr"},{"id":"2606.16667","title":"Look Again Before You Abstain:Budgeted Conformal Evidence Acquisition for Reliable Vision-Language Model","created":"2026-06-15","cited_by_count":3,"area":"mllm"},{"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":"2507.21406","title":"Shapley Uncertainty in Natural Language Generation","created":"2025-07-29","cited_by_count":2,"area":"alignment"},{"id":"2509.15356","title":"Predicting Language Models' Success at Zero-Shot Probabilistic Prediction","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2509.23002","title":"Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty","created":"2025-09-26","cited_by_count":2,"area":"synth"},{"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":"2510.22931","title":"Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining","created":"2025-10-27","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":"2602.03787","title":"Inference-time Unlearning Using Conformal Prediction","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2605.30085","title":"Conformal Certification of Reasoning Trace Prefixes","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"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":"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":"2505.13553","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":"2507.02256","title":"Uncertainty-aware Reward Design Process","created":"2025-07-03","cited_by_count":1,"area":"lr"},{"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":"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":"2605.15416","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}],"next_cursor":"100"}