{"total":121,"rows":[{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131,"area":null},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126,"area":null},{"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":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92,"area":null},{"id":"2401.05654","title":"Towards Conversational Diagnostic AI","created":"2024-01-11","cited_by_count":79,"area":null},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59,"area":null},{"id":"2310.06430","title":"Conformal Prediction for Deep Classifier via Label Ranking","created":"2023-10-10","cited_by_count":53,"area":null},{"id":"2405.01976","title":"Conformal Prediction for Natural Language Processing: A Survey","created":"2024-05-03","cited_by_count":53,"area":null},{"id":"2404.04689","title":"Multicalibration for Confidence Scoring in LLMs","created":"2024-04-06","cited_by_count":46,"area":null},{"id":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35,"area":null},{"id":"2402.15406","title":"Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2509.18658","title":"Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction","created":"2025-09-23","cited_by_count":27,"area":null},{"id":"2410.06494","title":"Conformal Prediction: A Data Perspective","created":"2024-10-09","cited_by_count":25,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2502.03609","title":"Multivariate Conformal Prediction using Optimal Transport","created":"2025-02-05","cited_by_count":22,"area":null},{"id":"2310.10299","title":"Forking Uncertainties: Reliable Prediction and Model Predictive Control with Sequence Models via Conformal Risk Control","created":"2023-10-16","cited_by_count":20,"area":null},{"id":"2407.04407","title":"Trustworthy Classification through Rank-Based Conformal Prediction Sets","created":"2024-07-05","cited_by_count":20,"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":"2311.13628","title":"Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2403.16527","title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","created":"2024-03-25","cited_by_count":17,"area":null},{"id":"2309.03797","title":"Conformal Autoregressive Generation: Beam Search with Coverage Guarantees","created":"2023-09-07","cited_by_count":16,"area":null},{"id":"2402.00251","title":"Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning","created":"2024-02-01","cited_by_count":16,"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":"2409.15844","title":"Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection","created":"2024-09-24","cited_by_count":15,"area":null},{"id":"2406.10490","title":"Active, anytime-valid risk controlling prediction sets","created":"2024-06-15","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":"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":"2402.02629","title":"PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks","created":"2024-02-04","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":"2402.12683","title":"TorchCP: A Python Library for Conformal Prediction","created":"2024-02-20","cited_by_count":9,"area":null},{"id":"2505.17773","title":"C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2405.14064","title":"Building a stable classifier with the inflated argmax","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2404.11350","title":"Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference","created":"2024-04-17","cited_by_count":7,"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":"2512.01556","title":"LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems","created":"2025-12-01","cited_by_count":7,"area":null},{"id":"2603.06616","title":"RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models","created":"2026-02-20","cited_by_count":7,"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":"2409.01236","title":"Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2505.19587","title":"WQLCP: Weighted Adaptive Conformal Prediction for Robust Uncertainty Quantification Under Distribution Shifts","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2506.10077","title":"A quantum semantic framework for natural language processing","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2509.12527","title":"Selective Risk Certification for LLM Outputs via Information-Lift Statistics: PAC-Bayes, Robustness, and Skeleton Design","created":"2025-09-16","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":"2404.14642","title":"Uncertainty Quantification on Graph Learning: A Survey","created":"2024-04-23","cited_by_count":4,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","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":"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":"2506.12202","title":"Quasar: A Programming Language Specialized for LLM Code Actions","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2602.16162","title":"LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers","created":"2026-02-18","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":"2403.16871","title":"Conformal Off-Policy Prediction for Multi-Agent Systems","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2407.06390","title":"JANET: Joint Adaptive predictioN-region Estimation for Time-series","created":"2024-07-08","cited_by_count":3,"area":null},{"id":"2505.24038","title":"Conformal Object Detection by Sequential Risk Control","created":"2025-05-29","cited_by_count":3,"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":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.16376","title":"Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2604.15302","title":"Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2606.08277","title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2509.24095","title":"Singleton-Optimized Conformal Prediction","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2511.00527","title":"A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models","created":"2025-11-01","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":"2605.16407","title":"Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture","created":"2026-05-13","cited_by_count":2,"area":null},{"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":"2606.05551","title":"Conformal Risk-Averse Decision Making with Action Conditional Guarantee","created":"2026-06-04","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":"2402.15929","title":"Certifying Knowledge Comprehension in LLMs","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2405.11968","title":"Conditional Shift-Robust Conformal Prediction for Graph Neural Network","created":"2024-05-20","cited_by_count":1,"area":null},{"id":"2408.04759","title":"Confident magnitude-based neural network pruning","created":"2024-08-08","cited_by_count":1,"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":"2512.22682","title":"Conformal Prediction Sets for Next-Token Prediction in Large Language Models: Balancing Coverage Guarantees with Set Efficiency","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.05219","title":"CAOS: Conformal Aggregation of One-Shot Predictors","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.20090","title":"Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2603.07371","title":"ConfHit: Conformal Generative Design with Oracle Free Guarantees","created":"2026-03-07","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":"2605.08077","title":"Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.23189","title":"Empirical Bayes Conformal Prediction for Vision and Language Models","created":"2026-05-22","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":"2606.00251","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":"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":"2608.05064","title":"Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models","created":"2026-08-05","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":"2507.14760","title":"QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2509.04733","title":"CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2510.04406","title":"Decomposition-Based Modular Conformal Prediction for Two-Stage Modeling","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2602.13264","title":"Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models","created":"2026-02-04","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":"2603.03971","title":"No Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.14345","title":"PAC-CF: Calibrating Irreversible Frontier Pruning in LLM-Guided Search","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.17143","title":"SeekerGym: A Benchmark for Reliable Information Seeking","created":"2026-04-18","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}],"next_cursor":"100"}