{"total":54,"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":"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":"2501.00555","title":"Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction","created":"2024-12-31","cited_by_count":18,"area":null},{"id":"2601.15778","title":"Agentic Confidence Calibration","created":"2026-01-22","cited_by_count":15,"area":"agents"},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2505.20047","title":"Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks","created":"2025-05-26","cited_by_count":10,"area":"lr"},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2604.16830","title":"The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation","created":"2026-04-18","cited_by_count":9,"area":"distill"},{"id":"2605.30834","title":"Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring","created":"2026-05-29","cited_by_count":9,"area":"vla"},{"id":"2505.03788","title":"Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding","created":"2025-04-30","cited_by_count":8,"area":"mllm"},{"id":"2603.25052","title":"Closing the Confidence-Faithfulness Gap in Large Language Models","created":"2026-03-26","cited_by_count":8,"area":"mechinterp"},{"id":"2510.08517","title":"CaRT: Teaching LLM Agents to Know When They Know Enough","created":"2025-10-09","cited_by_count":7,"area":"agents"},{"id":"2604.02543","title":"Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation","created":"2026-04-02","cited_by_count":6,"area":"mllm"},{"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":"2503.10628","title":"Uncertainty in Action: Confidence Elicitation in Embodied Agents","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2505.13946","title":"Visual Instruction Bottleneck Tuning","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2501.16718","title":"Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection","created":"2025-01-28","cited_by_count":4,"area":null},{"id":"2511.11169","title":"Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA","created":"2025-11-14","cited_by_count":4,"area":"agents"},{"id":"2604.17274","title":"Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models","created":"2026-04-19","cited_by_count":4,"area":"mllm"},{"id":"2505.11804","title":"Are vision language models robust to uncertain inputs?","created":"2025-05-17","cited_by_count":3,"area":"mllm"},{"id":"2507.06489","title":"On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2512.05456","title":"Do We Really Even Need Data? A Modern Look at Drawing Inference with Predicted Data","created":"2025-12-05","cited_by_count":3,"area":null},{"id":"2408.11249","title":"The Dilemma of Uncertainty Estimation for General Purpose AI in the EU AI Act","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2410.14975","title":"Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation","created":"2024-10-19","cited_by_count":2,"area":"mllm"},{"id":"2511.19768","title":"Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering","created":"2025-11-24","cited_by_count":2,"area":"mllm"},{"id":"2412.17411","title":"Pretraining with random noise for uncertainty calibration","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2507.07511","title":"Uncertainty Quantification for Motor Imagery BCI -- Machine Learning vs. Deep Learning","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2602.18867","title":"Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2604.25855","title":"SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring","created":"2026-04-28","cited_by_count":1,"area":"mllm"},{"id":"2605.15588","title":"Calibrating LLMs with Semantic-level Reward","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2504.12098","title":"Gauging Overprecision in LLMs: An Empirical Study","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2507.21521","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","created":"2025-07-29","cited_by_count":0,"area":"mllm"},{"id":"2509.25844","title":"Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations","created":"2025-09-30","cited_by_count":0,"area":"mllm"},{"id":"2602.15769","title":"ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution","created":"2026-02-17","cited_by_count":0,"area":"mllm"},{"id":"2603.09985","title":"The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.26769","title":"Edge Reliability Gap in Vision-Language Models: Quantifying Failure Modes of Compressed VLMs Under Visual Corruption","created":"2026-03-24","cited_by_count":0,"area":"mllm"},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.02010","title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.26689","title":"PinPoint: Prompting with Informative Interior Points","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2605.30506","title":"VLM-GLoc: Vision-Language Model Enhanced Monte Carlo Localization for Robust Semantic Global Localization in Cluttered Quasi-Static Environments","created":"2026-05-28","cited_by_count":0,"area":"mllm"},{"id":"2606.31407","title":"Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"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":"2607.22034","title":"Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation","created":"2026-07-24","cited_by_count":0,"area":"mllm"},{"id":"2607.24440","title":"Bigger or Cheaper? Scale and Quantization Effects on Uncertainty Signals in Vision-Language Models Under Image Degradation","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2608.09080","title":"When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Information","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.23845","title":"Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.31022","title":"MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.17882","title":"Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery?","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.24881","title":"Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.34270","title":"Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02695","title":"Test-time Calibration Learning for Large Language Model Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.02740","title":"Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.19226","title":"Agentic Self-Awareness: Aligning Knowing, Acting, and Holding","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}