{"total":76,"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":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"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":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67,"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":"2410.13640","title":"Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation","created":"2024-10-17","cited_by_count":57,"area":null},{"id":"2410.14582","title":"Do LLMs estimate uncertainty well in instruction-following?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23,"area":"moe"},{"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":"2502.21239","title":"Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs","created":"2025-02-28","cited_by_count":20,"area":null},{"id":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2411.00299","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","created":"2024-11-01","cited_by_count":16,"area":"mllm"},{"id":"2509.13813","title":"Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs","created":"2025-09-17","cited_by_count":13,"area":null},{"id":"2410.17234","title":"Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy","created":"2024-10-22","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":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2604.17112","title":"Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification","created":"2026-04-18","cited_by_count":10,"area":"lr"},{"id":"2408.12249","title":"LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction","created":"2024-08-22","cited_by_count":9,"area":"lr"},{"id":"2505.16113","title":"Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools","created":"2025-05-22","cited_by_count":9,"area":"agents"},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2510.02259","title":"Transformers Discover Molecular Structure Without Graph Priors","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2410.13047","title":"LLM Confidence Evaluation Measures in Zero-Shot CSS Classification","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2506.05497","title":"Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2510.11483","title":"Uncertainty Quantification for Retrieval-Augmented Reasoning","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"id":"2502.04643","title":"Confidence Elicitation: A New Attack Vector for Large Language Models","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2508.20384","title":"Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM","created":"2025-08-28","cited_by_count":5,"area":"lr"},{"id":"2509.24988","title":"Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2601.22548","title":"Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2409.09536","title":"VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2506.12202","title":"Quasar: A Programming Language Specialized for LLM Code Actions","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2509.23088","title":"The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2601.07006","title":"LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systems","created":"2026-01-11","cited_by_count":4,"area":null},{"id":"2602.04577","title":"Semantic Self-Distillation for Language Model Uncertainty","created":"2026-02-04","cited_by_count":4,"area":"distill"},{"id":"2604.01170","title":"Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning","created":"2026-04-01","cited_by_count":4,"area":"lr"},{"id":"2411.03497","title":"Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2505.01766","title":"Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2505.08662","title":"Revealing economic facts: LLMs know more than they say","created":"2025-05-13","cited_by_count":3,"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":"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":"2510.24831","title":"The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2507.21406","title":"Shapley Uncertainty in Natural Language Generation","created":"2025-07-29","cited_by_count":2,"area":"alignment"},{"id":"2508.05660","title":"Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review","created":"2025-07-30","cited_by_count":2,"area":"rag"},{"id":"2509.20415","title":"Online-Optimized RAG for Tool Use and Function Calling","created":"2025-09-24","cited_by_count":2,"area":"rag"},{"id":"2510.13750","title":"Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation","created":"2025-10-15","cited_by_count":2,"area":"rag"},{"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":"2512.24562","title":"HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering","created":"2025-12-31","cited_by_count":2,"area":null},{"id":"2606.22792","title":"The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2409.06601","title":"LaMsS: When Large Language Models Meet Self-Skepticism","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2506.06540","title":"Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches","created":"2025-06-06","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":"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":"2603.20632","title":"Optimal low-rank stochastic gradient estimation for LLM training","created":"2026-03-21","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":"2605.06444","title":"SCRuB: Social Concept Reasoning under Rubric-Based Evaluation","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.22864","title":"Reading Calibrated Uncertainty from Language Model Trajectories","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.31220","title":"Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.12587","title":"Strategic Decision Support for AI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2406.10263","title":"A Lightweight Framework for Adaptive Retrieval In Code Completion With Critique Model","created":"2024-06-11","cited_by_count":0,"area":"rag"},{"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":"2505.08902","title":"Performance Gains of LLMs With Humans in a World of LLMs Versus Humans","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2505.13273","title":"EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion","created":"2025-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2507.03998","title":"Toward Better Generalisation in Uncertainty Estimators: Leveraging Data-Agnostic Features","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2508.00600","title":"A Context-Aware Dual-Metric Framework for Confidence Estimation in Large Language Models","created":"2025-08-01","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":"2511.03047","title":"Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2512.05461","title":"Knowing Your Uncertainty -- On the application of LLM in social sciences","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2605.12240","title":"No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.28740","title":"Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Models in Clinical Text","created":"2026-05-27","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":"2607.20529","title":"Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.22839","title":"Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2610.08901","title":"Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.20292","title":"Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}