{"total":136,"rows":[{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974,"area":null},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323,"area":null},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293,"area":null},{"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":"2311.07383","title":"LM-Polygraph: Uncertainty Estimation for Language Models","created":"2023-11-13","cited_by_count":131,"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":"2409.17504","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","created":"2024-09-26","cited_by_count":99,"area":null},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2312.09300","title":"Self-Evaluation Improves Selective Generation in Large Language Models","created":"2023-12-14","cited_by_count":76,"area":null},{"id":"2305.14613","title":"Selectively Answering Ambiguous Questions","created":"2023-05-24","cited_by_count":66,"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":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2410.13640","title":"Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation","created":"2024-10-17","cited_by_count":57,"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":"2310.11689","title":"Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs","created":"2023-10-18","cited_by_count":50,"area":null},{"id":"2503.01917","title":"Steer LLM Latents for Hallucination Detection","created":"2025-03-01","cited_by_count":50,"area":null},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46,"area":null},{"id":"2402.18048","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","created":"2024-02-28","cited_by_count":45,"area":null},{"id":"2302.06235","title":"A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models","created":"2023-02-13","cited_by_count":39,"area":null},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2402.03502","title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","created":"2024-02-05","cited_by_count":36,"area":null},{"id":"2507.16488","title":"ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs","created":"2025-07-22","cited_by_count":32,"area":null},{"id":"2305.03236","title":"A Survey on Out-of-Distribution Detection in NLP","created":"2023-05-05","cited_by_count":31,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2404.12452","title":"Characterizing LLM Abstention Behavior in Science QA with Context Perturbations","created":"2024-04-18","cited_by_count":26,"area":null},{"id":"2304.08653","title":"On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study","created":"2023-04-17","cited_by_count":25,"area":null},{"id":"2308.02282","title":"DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization","created":"2023-08-04","cited_by_count":24,"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":"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":"2501.10858","title":"Reliable Text-to-SQL with Adaptive Abstention","created":"2025-01-18","cited_by_count":20,"area":null},{"id":"2504.07863","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","created":"2025-04-10","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":"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":"2403.15879","title":"TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring","created":"2024-03-23","cited_by_count":17,"area":null},{"id":"2310.01819","title":"TP2O: Creative Text Pair-to-Object Generation using Balance Swap-Sampling","created":"2023-10-03","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":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16,"area":null},{"id":"2406.07212","title":"Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Models","created":"2024-06-11","cited_by_count":16,"area":null},{"id":"2603.16459","title":"DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning","created":"2026-03-17","cited_by_count":15,"area":null},{"id":"2406.13230","title":"Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding","created":"2024-06-19","cited_by_count":14,"area":null},{"id":"2310.08027","title":"Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection","created":"2023-10-12","cited_by_count":13,"area":null},{"id":"2310.09586","title":"Causality and Independence Enhancement for Biased Node Classification","created":"2023-10-14","cited_by_count":13,"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":"2503.05757","title":"Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models","created":"2025-02-22","cited_by_count":12,"area":null},{"id":"2501.09527","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","created":"2025-01-16","cited_by_count":11,"area":null},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","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":"2411.08534","title":"Neural Topic Modeling with Large Language Models in the Loop","created":"2024-11-13","cited_by_count":10,"area":null},{"id":"2501.09345","title":"Rational Tuning of LLM Cascades via Probabilistic Modeling","created":"2025-01-16","cited_by_count":10,"area":null},{"id":"2311.09006","title":"Data Similarity is Not Enough to Explain Language Model Performance","created":"2023-11-15","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":"2504.09482","title":"HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs","created":"2025-04-13","cited_by_count":8,"area":null},{"id":"2510.01274","title":"TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2404.16954","title":"Taming False Positives in Out-of-Distribution Detection with Human Feedback","created":"2024-04-25","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":"2405.18635","title":"When and How Does In-Distribution Label Help Out-of-Distribution Detection?","created":"2024-05-28","cited_by_count":6,"area":null},{"id":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2502.08663","title":"Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis","created":"2025-02-10","cited_by_count":6,"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":"2506.21849","title":"The Consistency Hypothesis in Uncertainty Quantification for Large Language Models","created":"2025-06-27","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":"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":"2601.23188","title":"Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience","created":"2026-01-30","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":"2212.09928","title":"Improving the Robustness of Summarization Models by Detecting and Removing Input Noise","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2406.03158","title":"CSS: Contrastive Semantic Similarity for Uncertainty Quantification of LLMs","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2408.04851","title":"Your Classifier Can Be Secretly a Likelihood-Based OOD Detector","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2409.09629","title":"Confidence Estimation for LLM-Based Dialogue State Tracking","created":"2024-09-15","cited_by_count":4,"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":"2502.14268","title":"MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2505.15386","title":"RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2601.14210","title":"DRIFT: Detecting Representational Inconsistencies for Factual Truthfulness","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2303.09989","title":"Finding Competence Regions in Domain Generalization","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2402.05939","title":"Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2506.01512","title":"Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2507.14649","title":"Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs","created":"2025-07-19","cited_by_count":3,"area":null},{"id":"2509.15339","title":"Quantifying Genuine Awareness in Hallucination Prediction Beyond Question-Side Shortcuts","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2601.10398","title":"LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries","created":"2026-01-15","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":"2602.07842","title":"Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers","created":"2026-02-08","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":"2505.22803","title":"CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.17748","title":"HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2509.04655","title":"Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2510.06505","title":"Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics","created":"2025-10-07","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":"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":"2605.15393","title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.22007","title":"Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer","created":"2026-05-21","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":"2311.08598","title":"$DA^3$: A Distribution-Aware Adversarial Attack against Language Models","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2409.18645","title":"The Craft of Selective Prediction: Towards Reliable Case Outcome Classification -- An Empirical Study on European Court of Human Rights Cases","created":"2024-09-27","cited_by_count":1,"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}],"next_cursor":"100"}