{"total":90,"rows":[{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2403.04696","title":"Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification","created":"2024-03-07","cited_by_count":162,"area":null},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126,"area":null},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121,"area":null},{"id":"2406.15627","title":"Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph","created":"2024-06-21","cited_by_count":105,"area":null},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81,"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":"2410.15326","title":"A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice","created":"2024-10-20","cited_by_count":55,"area":null},{"id":"2402.10189","title":"Uncertainty Quantification for In-Context Learning of Large Language Models","created":"2024-02-15","cited_by_count":45,"area":null},{"id":"2407.17023","title":"DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models","created":"2024-07-24","cited_by_count":34,"area":null},{"id":"2502.04964","title":"Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency","created":"2025-02-07","cited_by_count":30,"area":null},{"id":"2506.00245","title":"Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity","created":"2025-05-30","cited_by_count":28,"area":null},{"id":"2410.14582","title":"Do LLMs estimate uncertainty well in instruction-following?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2508.08285","title":"The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2406.06950","title":"A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation","created":"2024-06-11","cited_by_count":21,"area":null},{"id":"2504.13677","title":"Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results","created":"2025-04-18","cited_by_count":21,"area":null},{"id":"2505.08200","title":"A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs","created":"2025-05-13","cited_by_count":21,"area":null},{"id":"2410.14309","title":"LoGU: Long-form Generation with Uncertainty Expressions","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2410.14746","title":"Accounting for Sycophancy in Language Model Uncertainty Estimation","created":"2024-10-17","cited_by_count":18,"area":null},{"id":"2502.14427","title":"Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models","created":"2025-02-20","cited_by_count":18,"area":null},{"id":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16,"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":"2505.16922","title":"UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2402.12146","title":"Enabling Weak LLMs to Judge Response Reliability via Meta Ranking","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2408.10692","title":"Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models","created":"2024-08-20","cited_by_count":9,"area":null},{"id":"2506.04089","title":"AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment","created":"2025-06-04","cited_by_count":9,"area":null},{"id":"2507.06196","title":"UQLM: A Python Package for Uncertainty Quantification in Large Language Models","created":"2025-07-08","cited_by_count":9,"area":null},{"id":"2406.07007","title":"Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference","created":"2024-06-11","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":"2510.02279","title":"Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2605.21801","title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2502.18050","title":"Uncertainty-aware abstention in medical diagnosis based on medical texts","created":"2025-02-25","cited_by_count":6,"area":null},{"id":"2505.20295","title":"SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2508.05534","title":"CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation","created":"2025-08-07","cited_by_count":6,"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":"2503.23175","title":"Large Language Models Are Unreliable for Cyber Threat Intelligence","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2505.19060","title":"UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2502.11115","title":"Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability","created":"2025-02-16","cited_by_count":4,"area":null},{"id":"2503.01688","title":"When an LLM is apprehensive about its answers -- and when its uncertainty is justified","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2503.06709","title":"Delusions of Large Language Models","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2505.23183","title":"Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2507.08203","title":"TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2405.13845","title":"Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2408.14229","title":"Holistic Uncertainty Estimation For Open-Set Recognition","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2509.16696","title":"Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2510.02339","title":"Evaluating Uncertainty Quantification Methods in Argumentative Large Language Models","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2511.03166","title":"Measuring Aleatoric and Epistemic Uncertainty in LLMs: Empirical Evaluation on ID and OOD QA Tasks","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2512.09538","title":"Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2512.24560","title":"Localized Calibrated Uncertainty in Code Language Models","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2602.00279","title":"Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2502.08631","title":"Ensemble based approach to quantifying uncertainty of LLM based classifications","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2505.22803","title":"CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2505.23996","title":"Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.21220","title":"Complexity-aware fine-tuning","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2508.18651","title":"Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2510.13836","title":"SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2602.11166","title":"Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2603.29693","title":"Measuring (some aspects of) the metacognition of AI","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2606.27679","title":"From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.20526","title":"ConfidenceBench: Evaluating Confidence Calibration in Large Language Models","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2407.02138","title":"Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2407.05718","title":"A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2505.15443","title":"ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.07309","title":"PIE: Performance Interval Estimation for Free-Form Generation Tasks","created":"2025-09-09","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":"2604.15741","title":"Learning Uncertainty from Sequential Internal Dispersion in Large Language Models","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.26139","title":"HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2606.20662","title":"Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2608.18115","title":"Temporal Multi-Signal Fusion for Token-Level Hallucination Detection","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.28930","title":"The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2404.10481","title":"BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2510.01251","title":"Efficient Uncertainty Estimation for LLM-based Entity Linking in Tabular Data","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2601.00680","title":"Sigmoid Head for Quality Estimation under Language Ambiguity","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2604.03473","title":"Evolutionary Search for Automated Design of Uncertainty Quantification Methods","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.05348","title":"From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.08560","title":"Uncertainty Estimation for the Open-Set Text Classification systems","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.10495","title":"Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.11328","title":"Epistemic Uncertainty for Test-Time Discovery","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.27016","title":"How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.19353","title":"Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2608.11138","title":"Attention-Path Fragility as an Uncertainty Signal in Large Language Models","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.14659","title":"When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.15992","title":"Optimal Model Activation Policies for Inference Networks of Large Language Models","created":"2026-07-07","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":"2609.26468","title":"How to Estimate Whether You Have Found Several Needles in a Haystack: Measuring Calibration in Multi-Label Text Classification","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33179","title":"Scoring the Wrong Question: Readout Failures in Constrained-Option Evaluation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35043","title":"Mixed-Prior Decision Risk for Open-Set Recognition","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00827","title":"Verbalized and Internal Probabilities Are Coupled in Large Language Models","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.06012","title":"Spectral Geometry of Attention: From Information Routing to Uncertainty","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}