{"total":43,"rows":[{"id":"2404.10193","title":"Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering","created":"2024-04-16","cited_by_count":32,"area":"mllm"},{"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":"2407.07840","title":"Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison","created":"2024-07-10","cited_by_count":7,"area":"mllm"},{"id":"2603.09018","title":"Meissa: Multi-modal Medical Agentic Intelligence","created":"2026-03-09","cited_by_count":6,"area":"mllm"},{"id":"2608.13167","title":"TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint","created":"2026-08-13","cited_by_count":5,"area":"mllm"},{"id":"2412.09718","title":"BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation","created":"2024-12-12","cited_by_count":3,"area":"mllm"},{"id":"2505.23745","title":"To Trust Or Not To Trust Your Vision-Language Model's Prediction","created":"2025-05-29","cited_by_count":3,"area":"mllm"},{"id":"2601.00138","title":"Explicit Abstention Knobs for Predictable Reliability in Video Question Answering","created":"2025-12-31","cited_by_count":3,"area":"mllm"},{"id":"2606.16667","title":"Look Again Before You Abstain:Budgeted Conformal Evidence Acquisition for Reliable Vision-Language Model","created":"2026-06-15","cited_by_count":3,"area":"mllm"},{"id":"2509.08777","title":"Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles","created":"2025-09-10","cited_by_count":2,"area":"mllm"},{"id":"2512.03101","title":"ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification","created":"2025-12-01","cited_by_count":2,"area":"mllm"},{"id":"2601.21662","title":"Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching","created":"2026-01-29","cited_by_count":2,"area":"mllm"},{"id":"2609.00868","title":"The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence","created":"2026-09-01","cited_by_count":2,"area":"mllm"},{"id":"2506.16724","title":"The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models","created":"2025-06-20","cited_by_count":1,"area":"mllm"},{"id":"2603.19790","title":"Geometric Risk Control for Vision-Language Model OCR","created":"2026-03-20","cited_by_count":1,"area":"mllm"},{"id":"2604.12035","title":"When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMs","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2604.25855","title":"SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring","created":"2026-04-28","cited_by_count":1,"area":"mllm"},{"id":"2605.00326","title":"Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification","created":"2026-05-01","cited_by_count":1,"area":"mllm"},{"id":"2606.00435","title":"Detect Before You Leap: Mirage Detection in Vision-Language Models","created":"2026-05-29","cited_by_count":1,"area":"mllm"},{"id":"2608.16690","title":"AnchorScore: A CLIP-Based Diagnostic of MLLM Annotation Difficulty","created":"2026-08-17","cited_by_count":1,"area":"mllm"},{"id":"2608.28726","title":"Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2602.13289","title":"Evaluating the Impact of Post-Training Quantization on Reliable VQA with Multimodal LLMs","created":"2026-02-08","cited_by_count":0,"area":"mllm"},{"id":"2605.06339","title":"A Regime Theory of Controller Class Selection for LLM Action Decisions","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2606.04922","title":"Geometry-Aware Distillation for Prompt Tuning Biomedical Vision-Language Models","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.15782","title":"Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference","created":"2026-06-14","cited_by_count":0,"area":"mllm"},{"id":"2606.25838","title":"Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines","created":"2026-06-24","cited_by_count":0,"area":"mllm"},{"id":"2606.29232","title":"When Does Synthetic CT Transfer? A Label-Free Donor/Host Diagnostic for Medical Vision-Language Model Routing on Real Lung CT","created":"2026-06-28","cited_by_count":0,"area":"mllm"},{"id":"2607.06254","title":"VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection","created":"2026-07-07","cited_by_count":0,"area":"mllm"},{"id":"2607.27667","title":"Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.04509","title":"CARGO-VL: Counterfactual Arbitration with Risk-Constrained Group Optimization for Vision-Language Models","created":"2026-08-05","cited_by_count":0,"area":"mllm"},{"id":"2608.06532","title":"Confidence Estimation for Financial Vision-Language Models in Chart and Document Understanding","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2608.07550","title":"Auditing Medical Vision-Language Models on Chest Radiographs: Estimating Reference Agreement Across Institutions","created":"2026-08-01","cited_by_count":0,"area":"mllm"},{"id":"2608.19376","title":"Does Marginal Coverage Guarantee Class-Conditional Safety for Zero-Shot VLMs Under Shift?","created":"2026-08-19","cited_by_count":0,"area":"mllm"},{"id":"2608.29193","title":"HalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide","created":"2026-08-29","cited_by_count":0,"area":"mllm"},{"id":"2609.01375","title":"IntroConformal: Conformal Factuality Guarantees for Large Vision-Language Models via Introspective Signals","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2609.04276","title":"FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.11022","title":"New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models","created":"2026-09-10","cited_by_count":0,"area":"mllm"},{"id":"2609.15706","title":"Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction","created":"2026-09-14","cited_by_count":0,"area":"mllm"},{"id":"2609.21763","title":"Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis Screening","created":"2026-09-18","cited_by_count":0,"area":"mllm"},{"id":"2609.26093","title":"RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2610.01243","title":"When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts","created":"2026-10-01","cited_by_count":0,"area":"mllm"},{"id":"2610.16465","title":"Teaching Vision-Language Models to Decline: Support Completion Against Mirage","created":"2026-10-12","cited_by_count":0,"area":"mllm"},{"id":"2610.20107","title":"Why Generate a Click? Plug-in Decision Heads for Web Agents","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}