mlsanityData to 14 Oct 2026

VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation

arXiv 2411.11919 ↗First posted 18 Nov 2024cs.CVcited by 73

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we introduce VL-Uncertainty, the first uncertainty-based framework for detecting hallucinations in LVLMs. Different from most existing methods that require ground-truth or pseudo annotations, VL-Uncertainty utilizes uncertainty as an intrinsic metric. We measure uncertainty by analyzing the prediction variance across semantically equivalent but perturbed prompts, including visual and textual data. When LVLMs are highly confident, they provide consistent responses to semantically equivalent queries. However, when uncertain, the responses of the target LVLM become more random. Considering semantically similar answers with different wordings, we cluster LVLM responses based on their semantic content and then calculate the cluster distribution entropy as the uncertainty measure to detect hallucination. Our extensive experiments on 10 LVLMs across four benchmarks, covering both free-form and multi-choice tasks, show that VL-Uncertainty significantly outperforms strong baseline methods in hallucination detection.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 50 of its 61 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

50 of 61 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Hallucination of Multimodal Large Language Models: A Survey29 Apr
  2. 2024Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback22 Apr
  3. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  4. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun
  5. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May

Other references · 45

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  9. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  10. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  11. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  12. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
33 more
  1. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  2. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  3. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  4. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  5. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  6. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  8. 2018Object Hallucination in Image Captioningcited by 669
  9. 2023NExT-GPT: Any-to-Any Multimodal LLMcited by 615
  10. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  11. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 490
  12. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 392
  13. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  14. 2023An Embodied Generalist Agent in 3D Worldcited by 365
  15. 2017Snapshot Ensembles: Train 1, get M for freecited by 350
  16. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 290
  17. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 280
  18. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  19. 2017Concrete Dropoutcited by 227
  20. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  21. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMcited by 184
  22. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 162
  23. 2023Osprey: Pixel Understanding with Visual Instruction Tuningcited by 159
  24. 2020Better Aggregation in Test-Time Augmentationcited by 122
  25. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  26. 2024A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Modelscited by 100
  27. 2024NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samplescited by 97
  28. 2020Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentationcited by 61
  29. 2020Learning Loss for Test-Time Augmentationcited by 56
  30. 2022Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularizationcited by 45
  31. 2024MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Modelscited by 15
  32. 2024Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modelingcited by 14
  33. 2024Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detectioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 24; 2026: 48.

73 papers.

Sort:

By area:

  1. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 95
  2. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 27
  3. 2025When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMscited by 21
  4. 2025MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLMcited by 17
  5. 2025Object Detection with Multimodal Large Vision-Language Models: An In-depth Reviewcited by 14
  6. 2025Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCRcited by 12
  7. 2025GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similaritycited by 11
  8. 2026VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learningcited by 9
  9. 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoringcited by 9
  10. 2025Calibrating Uncertainty Quantification of Multi-Modal LLMs using Groundingcited by 8
  11. 2026Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volumecited by 8
  12. 2026VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoningcited by 8
38 more
  1. 2025LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systemscited by 7
  2. 2025Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinkingcited by 6
  3. 2025Uncertainty in Action: Confidence Elicitation in Embodied Agentscited by 5
  4. 2025UniVRSE: Unified Vision-conditioned Response Semantic Entropy for Hallucination Detection in Medical Vision-Language Modelscited by 5
  5. 2025Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Modelscited by 5
  6. 2025HalDec-Bench: Benchmarking Hallucination Detector in Image Captioningcited by 5
  7. 2026VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluationcited by 5
  8. 2026Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Rankingcited by 5
  9. 2025Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMscited by 4
  10. 2025Semantic Reformulation Entropy for Robust Hallucination Detection in QA Taskscited by 4
  11. 2026BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generationcited by 4
  12. 2025Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Predictioncited by 3
  13. 2025Are vision language models robust to uncertain inputs?cited by 3
  14. 2025HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Modelscited by 3
  15. 2025When to Trust the Answer: Question-Aligned Semantic Nearest Neighbor Entropy for Safer Surgical VQAcited by 3
  16. 2026VLM-UQBench: A Benchmark for Modality-Specific and Cross-Modality Uncertainties in Vision Language Modelscited by 3
  17. 2026Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQAcited by 3
  18. 2024FastRM: An efficient and automatic explainability framework for multimodal generative modelscited by 2
  19. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  20. 2026VisTIRA: Closing the Image-Text Modality Gap in Visual Math Reasoning via Structured Tool Integrationcited by 2
  21. 2026Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasetscited by 2
  22. 2025Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Imagescited by 1
  23. 2025Analysis of Image-and-Text Uncertainty Propagation in Multimodal Large Language Models with Cardiac MR-Based Applicationscited by 1
  24. 2026FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answeringcited by 1
  25. 2026When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMscited by 1
  26. 2026Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classificationcited by 1
  27. 2026VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answeringcited by 1
  28. 2026FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertaintycited by 1
  29. 2026CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimationcited by 1
  30. 2025HalCECE: A Framework for Explainable Hallucination Detection through Conceptual Counterfactuals in Image Captioningcited by 0
  31. 2026Overthinking Causes Hallucination: Tracing Confounder Propagation in Vision Language Modelscited by 0
  32. 2026HalDec-Bench: Benchmarking Hallucination Detector in Image Captioningcited by 0
  33. 2026Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gaincited by 0
  34. 2026SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systemscited by 0
  35. 2026Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generationcited by 0
  36. 2026Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?cited by 0
  37. 2026Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?cited by 0
  38. 2026When Thinking Hurts: Epistemic Signals in the Reasoning Chains of Visual Language Modelscited by 0

50 most cited of 73 All 73 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Revisiting Hallucination Detection with Effective Rank-based Uncertainty
  2. 2024Reference-free Hallucination Detection for Large Vision-Language Models
  3. 2025Leveraging NTPs for Efficient Hallucination Detection in VLMs
  4. 2025Visual hallucination detection in large vision-language models via evidential conflict
  5. 2025Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models
  6. 2025MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs
  7. 2025On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
  8. 2026Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language Models