{"total":97,"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":"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":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62,"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":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2410.13246","title":"Atomic Calibration of LLMs in Long-Form Generations","created":"2024-10-17","cited_by_count":24,"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":"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":"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":"2504.19254","title":"Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers","created":"2025-04-27","cited_by_count":18,"area":null},{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"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":"2407.03572","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","created":"2024-07-04","cited_by_count":16,"area":null},{"id":"2410.01794","title":"Loki: An Open-Source Tool for Fact Verification","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2505.20045","title":"Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads","created":"2025-05-26","cited_by_count":16,"area":null},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2510.04849","title":"When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA","created":"2025-10-06","cited_by_count":14,"area":null},{"id":"2502.11948","title":"HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection","created":"2025-02-17","cited_by_count":13,"area":null},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","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":"2409.11283","title":"Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling","created":"2024-09-17","cited_by_count":9,"area":null},{"id":"2505.16894","title":"Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs","created":"2025-05-22","cited_by_count":9,"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":"2505.20295","title":"SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2412.04606","title":"Semantic Consistency-Based Uncertainty Quantification for Factuality in Radiology Report Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2504.18639","title":"Span-Level Hallucination Detection for LLM-Generated Answers","created":"2025-04-25","cited_by_count":5,"area":null},{"id":"2505.21115","title":"Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2411.08254","title":"Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy","created":"2024-11-13","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":"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":"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":"2511.20284","title":"Can LLMs Make (Personalized) Access Control Decisions?","created":"2025-11-25","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":"2502.11962","title":"Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.18562","title":"Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models","created":"2025-03-24","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":"2602.11877","title":"Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2503.18293","title":"Fact-checking AI-generated news reports: Can LLMs catch their own lies?","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2510.09347","title":"LLP: LLM-Based Product Pricing in E-commerce","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":"2601.09001","title":"Entropy Sentinel: Probing Entropy Traces for LLM Monitoring","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2605.10415","title":"Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2412.18377","title":"ChaI-TeA: A Benchmark for Evaluating Autocompletion of Interactions with LLM-based Chatbots","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2501.02842","title":"Foundations of GenIR","created":"2025-01-06","cited_by_count":1,"area":null},{"id":"2505.12265","title":"Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation","created":"2025-05-18","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":"2509.02198","title":"FActBench: A Benchmark for Fine-grained Automatic Evaluation of LLM-Generated Text in the Medical Domain","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.21118","title":"The Gray Zone of Faithfulness: Taming Ambiguity in Unfaithfulness Detection","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.00620","title":"Certain but not Probable? Differentiating Certainty from Probability in LLM Token Outputs for Probabilistic Scenarios","created":"2025-11-01","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":"2602.18671","title":"Spilled Energy in Large Language Models","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2602.18693","title":"Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.20161","title":"Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models","created":"2026-03-20","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":"2604.13991","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":"2410.07737","title":"Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data","created":"2024-10-10","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":"2507.20546","title":"Enhancing Hallucination Detection via Future Context","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2510.13143","title":"Stable LLM Ensemble: Interaction between Example Representativeness and Diversity","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2601.00348","title":"Robust Uncertainty Quantification for Factual Generation of Large Language Models","created":"2026-01-01","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":"2601.02574","title":"Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.15645","title":"Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation","created":"2026-01-22","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":"2604.07825","title":"Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders","created":"2026-04-09","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":"2604.10697","title":"Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models","created":"2026-04-12","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":"2605.05025","title":"Detecting Hallucinations in Large Language Models via Internal Attention Divergence Signals","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.05777","title":"Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.20490","title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","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":"2606.29545","title":"AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models","created":"2026-06-28","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":"2607.15607","title":"ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Language","created":"2026-07-17","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":"2607.17251","title":"VecFontLLM: Anchor-Guided Direct Synthesis of Chinese Vector Fonts","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.16353","title":"HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22483","title":"Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models","created":"2026-08-23","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":"2608.24492","title":"When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.30987","title":"Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.07095","title":"Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.37040","title":"Selecting The Most Informative Tokens in Natural Language Autoencoders","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.11300","title":"Characterizing Overconfident Failure in LLM-Based Code Generation","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16933","title":"Estimating Uncertainty of Omnimodal Large Language Models via External Omnimodal Embeddings","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19996","title":"Gray-Box Hallucination Detection in LLMs with Token Identities","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}