{"total":106,"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":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62,"area":null},{"id":"2406.11675","title":"BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models","created":"2024-06-17","cited_by_count":50,"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":"2406.04306","title":"Improving Uncertainty Estimation through Semantically Diverse Language Generation","created":"2024-06-06","cited_by_count":35,"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":"2508.08285","title":"The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2504.10063","title":"Hallucination Detection in LLMs with Topological Divergence on Attention Graphs","created":"2025-04-14","cited_by_count":19,"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":"2511.04418","title":"The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity","created":"2025-11-06","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":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16,"area":null},{"id":"2412.05723","title":"Training-Free Bayesianization for Low-Rank Adapters of Large Language Models","created":"2024-12-07","cited_by_count":12,"area":null},{"id":"2510.12040","title":"Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions","created":"2025-10-14","cited_by_count":11,"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":"2412.12767","title":"A Survey of Calibration Process for Black-Box LLMs","created":"2024-12-17","cited_by_count":8,"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":"2509.14478","title":"Estimating Semantic Alphabet Size for LLM Uncertainty Quantification","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2601.03042","title":"BaseCal: Unsupervised Confidence Calibration via Base Model Signals","created":"2026-01-06","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":"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":"2510.02671","title":"Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering","created":"2025-10-03","cited_by_count":7,"area":null},{"id":"2601.20026","title":"Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method","created":"2026-01-27","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":"2506.09684","title":"Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models","created":"2025-06-11","cited_by_count":6,"area":null},{"id":"2410.02173","title":"Efficiently Deploying LLMs with Controlled Risk","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2504.03579","title":"Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy","created":"2025-04-04","cited_by_count":5,"area":null},{"id":"2506.00344","title":"Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs","created":"2025-05-31","cited_by_count":5,"area":null},{"id":"2511.07694","title":"Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models","created":"2025-11-10","cited_by_count":5,"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":"2506.00637","title":"Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics","created":"2025-05-31","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":"2602.17431","title":"Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study","created":"2026-02-19","cited_by_count":4,"area":null},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2505.19073","title":"Towards Harmonized Uncertainty Estimation for Large Language Models","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2506.23603","title":"SoK: Semantic Privacy in Large Language Models","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2601.13284","title":"Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2601.21500","title":"Task-Awareness Improves LLM Generations and Uncertainty","created":"2026-01-29","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":"2602.12015","title":"Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.06922","title":"NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks","created":"2026-03-06","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":"2412.15683","title":"Variability Need Not Imply Error: The Case of Adequate but Semantically Distinct Responses","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2502.00507","title":"A statistically consistent measure of semantic uncertainty using Language Models","created":"2025-02-01","cited_by_count":2,"area":null},{"id":"2508.18473","title":"Principled Detection of Hallucinations in Large Language Models via Multiple Testing","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","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":"2601.01552","title":"HalluZig: Hallucination Detection using Zigzag Persistence","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2604.07172","title":"Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.12196","title":"Beyond Majority Voting: Efficient Best-Of-N with Radial Consensus Score","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2605.28778","title":"Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.19868","title":"A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models","created":"2026-06-18","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":"2505.12660","title":"Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.17855","title":"Explaining Sources of Uncertainty in Automated Fact-Checking","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.07448","title":"Extending Epistemic Uncertainty Beyond Parameters Would Assist in Designing Reliable LLMs","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2509.22612","title":"Beyond statistical significance: Quantifying uncertainty and statistical variability in multilingual and multitask NLP evaluation","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2510.21891","title":"Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.17081","title":"MUCH: A Multilingual Claim Hallucination Benchmark","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2512.04351","title":"Distance Is All You Need: Radial Dispersion for Uncertainty Estimation in Large Language Models","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2601.03270","title":"Advances and Challenges in Semantic Textual Similarity: A Comprehensive Survey","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2604.02830","title":"GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.06812","title":"AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation","created":"2026-04-08","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":"2605.05592","title":"When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation","created":"2026-05-07","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":"2606.08098","title":"When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference","created":"2026-06-06","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":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2502.07186","title":"PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2505.02311","title":"Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2506.16234","title":"Sequential Causal Discovery with Noisy Language Model Priors","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2510.04439","title":"On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2511.15005","title":"Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2601.19918","title":"Lowest Span Confidence: Zero-Shot Hallucination Detection from a Single LLM Response","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2602.07958","title":"Accuracy-Delay Trade-Off in LLM Offloading via Token-Level Uncertainty","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2602.17465","title":"Entropy-Based Data Selection for Language Models","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.25463","title":"CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2603.26363","title":"A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.08974","title":"Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.19162","title":"Mind the Unseen Mass: Unmasking LLM Hallucinations via Soft-Hybrid Alphabet Estimation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.04295","title":"LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.08516","title":"OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.19220","title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","created":"2026-05-19","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":"2605.28264","title":"Entropy Distribution as a Fingerprint for Hallucinations in Generative Models","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.09875","title":"Integrating Local and Global Entropy for Uncertainty Quantification in LLMs","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.05721","title":"SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.08377","title":"Eigenvalue Calibration for Semantic Embeddings of Large Language Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.12273","title":"Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.16868","title":"Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.00285","title":"Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.04899","title":"Evaluation Pitfalls and Sparsity Limitations in LLM-based Confidence Estimates for Classification","created":"2026-08-05","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":"2608.14653","title":"Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.19323","title":"Improved Confidence Estimates for Black-Box Large Language Models","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22506","title":"Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.23086","title":"POOL: Propagated Uncertainty Over Lookalikes","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.02275","title":"Do Large Language Models Capture the Diversity in their Training Data?","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":"100"}