{"total":97,"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":"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":"2404.15993","title":"Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach","created":"2024-04-24","cited_by_count":76,"area":null},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69,"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":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62,"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":"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":"2401.13744","title":"Conformal Prediction Sets Improve Human Decision Making","created":"2024-01-24","cited_by_count":35,"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":"2502.03609","title":"Multivariate Conformal Prediction using Optimal Transport","created":"2025-02-05","cited_by_count":22,"area":null},{"id":"2309.10092","title":"Conformal Temporal Logic Planning using Large Language Models","created":"2023-09-18","cited_by_count":21,"area":null},{"id":"2402.00707","title":"Non-Exchangeable Conformal Language Generation with Nearest Neighbors","created":"2024-02-01","cited_by_count":21,"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":"2402.15368","title":"Probabilistically Correct Language-based Multi-Robot Planning using Conformal Prediction","created":"2024-02-23","cited_by_count":18,"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":"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":"2601.12471","title":"Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty","created":"2026-01-18","cited_by_count":15,"area":null},{"id":"2505.13732","title":"Backward Conformal Prediction","created":"2025-05-19","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":"2502.17264","title":"Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage","created":"2025-02-24","cited_by_count":13,"area":null},{"id":"2402.04344","title":"Does confidence calibration improve conformal prediction?","created":"2024-02-06","cited_by_count":12,"area":null},{"id":"2502.13030","title":"Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization","created":"2025-02-18","cited_by_count":12,"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":"2504.21022","title":"ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guarantees","created":"2025-04-22","cited_by_count":11,"area":null},{"id":"2310.09926","title":"Estimating Uncertainty in Multimodal Foundation Models using Public Internet Data","created":"2023-10-15","cited_by_count":10,"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":"2502.16658","title":"Volume Optimality in Conformal Prediction with Structured Prediction Sets","created":"2025-02-23","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":"2505.17773","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":"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":"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":"2410.13047","title":"LLM Confidence Evaluation Measures in Zero-Shot CSS Classification","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2411.09289","title":"StreamAdapter: Efficient Test Time Adaptation from Contextual Streams","created":"2024-11-14","cited_by_count":6,"area":null},{"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":"2306.06221","title":"Conformalizing Machine Translation Evaluation","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2412.02904","title":"Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2503.10628","title":"Uncertainty in Action: Confidence Elicitation in Embodied Agents","created":"2025-03-13","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":"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":"2501.11031","title":"AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model","created":"2025-01-19","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":"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":"2509.21479","title":"Filtering with Confidence: When Data Augmentation Meets Conformal Prediction","created":"2025-09-25","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":"2311.06427","title":"ChatGPT Prompting Cannot Estimate Predictive Uncertainty in High-Resource Languages","created":"2023-11-10","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":"2603.03704","title":"Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning","created":"2026-03-04","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":"2606.15964","title":"PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift","created":"2026-06-14","cited_by_count":2,"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":"2605.22864","title":"Reading Calibrated Uncertainty from Language Model Trajectories","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.27091","title":"MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition","created":"2026-05-25","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":"2606.12587","title":"Strategic Decision Support for AI Agents","created":"2026-06-10","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":"2608.25824","title":"Localize-Then-Decide Guarantees for LLM Judgments","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2410.14010","title":"Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2503.23105","title":"Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments","created":"2025-03-29","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":"2512.02704","title":"Conformal Correction for Efficiency May be at Odds with Entropy","created":"2025-12-02","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":"2603.27403","title":"Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling","created":"2026-03-28","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":"2604.17143","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},{"id":"2605.12195","title":"Fair Conformal Classification via Learning Representation-Based Groups","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.12201","title":"Uncertainty Quantification for LLM-based Code Generation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.28264","title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.10539","title":"AI YOU Town: Make Friends and Money with Your Digital Twin","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.21623","title":"Cloud-Native Evaluation-as-a-Service: A Microservices Architecture for Scalable AI Monitoring with Conformal Guarantees","created":"2026-07-04","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":"2608.26529","title":"Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialogue","created":"2026-08-27","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":"2609.02095","title":"READY or Not: Reliable Enterprise Agent Deployment","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":"2610.04239","title":"Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.13276","title":"CopRoute: Dependence-Aware Conformal Routing for Language Models","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}