{"total":39,"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":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67,"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":"2505.17656","title":"Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2506.00823","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2506.09669","title":"Query-Level Uncertainty in Large Language Models","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2506.11887","title":"Cascaded Language Models for Cost-effective Human-AI Decision-Making","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2511.19933","title":"Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications","created":"2025-11-25","cited_by_count":10,"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":"2510.12587","title":"Teaching Language Models to Faithfully Express their Uncertainty","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2407.08388","title":"On the attribution of confidence to large language models","created":"2024-07-11","cited_by_count":5,"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":"2609.37470","title":"Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces","created":"2026-09-27","cited_by_count":3,"area":null},{"id":"2506.01698","title":"When LLMs Team Up: The Emergence of Collaborative Affective Computing","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2508.16267","title":"From Confidence to Collapse in LLM Factual Robustness","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2511.14783","title":"Human or LLM as Standardized Patients? A Comparative Study for Medical Education","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2606.27679","title":"From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models","created":"2026-06-26","cited_by_count":2,"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":"2606.01120","title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2609.04539","title":"A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2502.15714","title":"TrustDataFilter:Leveraging Trusted Knowledge Base Data for More Effective Filtering of Unknown Information","created":"2025-01-25","cited_by_count":0,"area":null},{"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":"2511.10119","title":"Intelligence Foundation Model: A New Perspective to Approach Artificial General Intelligence","created":"2025-11-13","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":"2602.08186","title":"Nexus: Inferring Join Graphs from Metadata Alone via Iterative Low-Rank Matrix Completion","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.15861","title":"CAST: Achieving Stable LLM-based Text Analysis for Data Analytics","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.22090","title":"Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.06197","title":"Bridging visual saliency and large language models for explainable deep learning in medical imaging","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.07827","title":"From token probabilities to calibrated confidence: An empirical study of mathematical question answering","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.26121","title":"Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2609.10122","title":"ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2610.02902","title":"LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05452","title":"VERA: Verdict-Conditioned Reliability for Adaptive LLM Judges","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}