{"total":79,"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":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115,"area":null},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114,"area":null},{"id":"2407.03282","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","created":"2024-07-03","cited_by_count":82,"area":null},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81,"area":null},{"id":"2306.01694","title":"Evaluating Language Models for Mathematics through Interactions","created":"2023-06-02","cited_by_count":70,"area":null},{"id":"2305.13712","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","created":"2023-05-23","cited_by_count":61,"area":null},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57,"area":null},{"id":"2406.00793","title":"Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective","created":"2024-06-02","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":"2402.11756","title":"MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs","created":"2024-02-19","cited_by_count":46,"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":"2306.04459","title":"Uncertainty in Natural Language Processing: Sources, Quantification, and Applications","created":"2023-06-05","cited_by_count":44,"area":null},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38,"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":"2404.09610","title":"LoRA Dropout as a Sparsity Regularizer for Overfitting Control","created":"2024-04-15","cited_by_count":35,"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":"2311.09731","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","created":"2023-11-16","cited_by_count":32,"area":null},{"id":"2407.14614","title":"Evaluating language models as risk scores","created":"2024-07-19","cited_by_count":27,"area":null},{"id":"2401.07348","title":"Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity","created":"2024-01-14","cited_by_count":21,"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":"2405.03425","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","created":"2024-05-06","cited_by_count":20,"area":null},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","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":"2406.00380","title":"HonestLLM: Toward an Honest and Helpful Large Language Model","created":"2024-06-01","cited_by_count":18,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2309.03797","title":"Conformal Autoregressive Generation: Beam Search with Coverage Guarantees","created":"2023-09-07","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":"2310.06680","title":"Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach","created":"2023-10-10","cited_by_count":15,"area":null},{"id":"2406.04370","title":"Large Language Model Confidence Estimation via Black-Box Access","created":"2024-06-01","cited_by_count":14,"area":null},{"id":"2501.17630","title":"Uncertainty Quantification and Decomposition for LLM-based Recommendation","created":"2025-01-29","cited_by_count":12,"area":null},{"id":"2402.04957","title":"Reconfidencing LLMs from the Grouping Loss Perspective","created":"2024-02-07","cited_by_count":11,"area":null},{"id":"2407.14767","title":"I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation","created":"2024-07-20","cited_by_count":11,"area":null},{"id":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2403.18286","title":"Few-Shot Recalibration of Language Models","created":"2024-03-27","cited_by_count":9,"area":null},{"id":"2310.06167","title":"Predictable Artificial Intelligence","created":"2023-10-09","cited_by_count":8,"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":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2507.07236","title":"Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2510.14077","title":"ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2405.00632","title":"When Quantization Affects Confidence of Large Language Models?","created":"2024-05-01","cited_by_count":5,"area":null},{"id":"2409.18461","title":"Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2501.18665","title":"BARNN: A Bayesian Autoregressive and Recurrent Neural Network","created":"2025-01-30","cited_by_count":5,"area":null},{"id":"2502.12122","title":"Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2402.13606","title":"MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models","created":"2024-02-21","cited_by_count":4,"area":null},{"id":"2402.17527","title":"Predict the Next Word: Humans exhibit uncertainty in this task and language models _____","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2408.05873","title":"Recognizing Limits: Investigating Infeasibility in Large Language Models","created":"2024-08-11","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":"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":"2406.05496","title":"Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities","created":"2024-06-08","cited_by_count":3,"area":null},{"id":"2406.10775","title":"A Rate-Distortion View of Uncertainty Quantification","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2509.07925","title":"GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2212.12411","title":"Benchmark for Uncertainty & Robustness in Self-Supervised Learning","created":"2022-12-23","cited_by_count":1,"area":null},{"id":"2402.14184","title":"Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2404.00758","title":"From Robustness to Improved Generalization and Calibration in Pre-trained Language Models","created":"2024-03-31","cited_by_count":1,"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":"2504.03640","title":"Bonsai: Interpretable Tree-Adaptive Grounded Reasoning","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2601.04277","title":"Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs","created":"2026-01-07","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":"2604.10189","title":"FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2608.21019","title":"Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2407.12626","title":"Domain-specific or Uncertainty-aware models: Does it really make a difference for biomedical text classification?","created":"2024-07-17","cited_by_count":0,"area":null},{"id":"2407.12850","title":"Limits to Predicting Online Speech Using Large Language Models","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2408.06736","title":"Speculations on Uncertainty and Humane Algorithms","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2410.12478","title":"MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2505.20485","title":"Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2509.19557","title":"Confidence Calibration in Large Language Model-Based Entity Matching","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2509.19563","title":"Uncertainty in Semantic Language Modeling with PIXELS","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.15233","title":"Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2602.13264","title":"Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.00022","title":"Noise reduction in BERT NER models for clinical entity extraction","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2603.27033","title":"RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.07706","title":"Bayesian Fine-tuning in Projected Subspaces","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.27747","title":"Soft Specialists: $\\alpha$-R\\'enyi Ensembles for Uncertainty-Aware LLM Post-Training","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.07419","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.30021","title":"Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}