mlsanityData to 7 Oct 2026

Visual Hallucinations of Multi-modal Large Language Models

arXiv 2402.14683 ↗First posted 22 Feb 2024cs.CV cs.AI cs.LGcited by 68

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

Abstract (arXiv)

Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines incorrect details about an image in visual question answering. Existing studies find VH instances only in existing image datasets, which results in biased understanding of MLLMs' performance under VH due to limited diversity of such VH instances. In this work, we propose a tool called VHTest to generate a diverse set of VH instances. Specifically, VHTest finds some initial VH instances in existing image datasets (e.g., COCO), generates a text description for each VH mode, and uses a text-to-image generative model (e.g., DALL-E-3) to generate VH images based on the text descriptions. We collect a benchmark dataset with 1,200 VH instances in 8 VH modes using VHTest. We find that existing MLLMs such as GPT-4V, LLaVA-1.5, and MiniGPT-v2 hallucinate for a large fraction of the instances in our benchmark. Moreover, we find that fine-tuning an MLLM using our benchmark dataset reduces its likelihood to hallucinate without sacrificing its performance on other benchmarks. Our benchmarks are publicly available: https://github.com/wenhuang2000/VHTest.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 30 of its 40 references that are in the map. First posted on arXiv 22 Feb 2024.

Builds on

30 of 40 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  2. 2023Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites4 Dec
  3. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Models24 Oct
  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 · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  8. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  9. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  10. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  11. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  12. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
13 more
  1. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
  2. 2024Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMscited by 719
  3. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  4. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  5. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  6. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  7. 2023Language Is Not All You Need: Aligning Perception with Language Modelscited by 543
  8. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  9. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 339
  10. 2021VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioningcited by 190
  11. 2023Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarkscited by 139
  12. 2022Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Trainingcited by 88
  13. 2023Mass-Producing Failures of Multimodal Systems with Language Modelscited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 22; 2025: 29; 2026: 17.

68 papers.

Sort:

By area:

  1. 2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 146
  2. 2024VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Modelscited by 88
  3. 2024A Survey on Benchmarks of Multimodal Large Language Modelscited by 81
  4. 2024Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Modelscited by 72
  5. 2024MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMscited by 72
  6. 2024BRAVE: Broadening the visual encoding of vision-language modelscited by 68
  7. 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Modelscited by 51
  8. 2024A Survey on Evaluation of Multimodal Large Language Modelscited by 46
  9. 2024Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projectioncited by 46
  10. 2025Visual Large Language Models for Generalized and Specialized Applicationscited by 35
  11. 2024Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectlycited by 29
  12. 2024Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Modelscited by 28
38 more
  1. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  2. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  3. 2025MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representationscited by 22
  4. 2025Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigationcited by 20
  5. 2025Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Markscited by 17
  6. 2024The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspectivecited by 14
  7. 2025Object Detection with Multimodal Large Vision-Language Models: An In-depth Reviewcited by 14
  8. 2025Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulationcited by 13
  9. 2025Learning to Steer: Input-dependent Steering for Multimodal LLMscited by 13
  10. 2024TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Modelscited by 12
  11. 2025Aligning Multimodal LLM with Human Preference: A Surveycited by 12
  12. 2024Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answeringcited by 11
  13. 2025Visual Jenga: Discovering Object Dependencies via Counterfactual Inpaintingcited by 11
  14. 2025MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibrationcited by 11
  15. 2025Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Modelscited by 9
  16. 2025Unified Multimodal Understanding via Byte-Pair Visual Encodingcited by 9
  17. 2024UniRAG: Universal Retrieval Augmentation for Large Vision Language Modelscited by 8
  18. 2025OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucinationcited by 8
  19. 2024A Survey of Automatic Hallucination Evaluation on Natural Language Generationcited by 7
  20. 2024Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuningcited by 6
  21. 2024Refusing Safe Prompts for Multi-modal Large Language Modelscited by 6
  22. 2025Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approachcited by 6
  23. 2026AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoningcited by 6
  24. 2026MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learningcited by 5
  25. 2025Is Extending Modality The Right Path Towards Omni-Modality?cited by 4
  26. 2025Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Modelscited by 4
  27. 2026FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMscited by 4
  28. 2024Explaining Multi-modal Large Language Models by Analyzing their Vision Perceptioncited by 3
  29. 2025Multimodal Language Models as Text-to-Image Model Evaluatorscited by 3
  30. 2025ChartAB: A Benchmark for Chart Grounding & Dense Alignmentcited by 3
  31. 2025V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Interventioncited by 3
  32. 2025Early Estimation of Language to Latent Alignment in Diffusion Modelscited by 3
  33. 2026Visual Enhanced Depth Scaling for Multimodal Latent Reasoningcited by 3
  34. 2026Latent Visual Cache for Video Reasoningcited by 3
  35. 2025Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Modelcited by 2
  36. 2025AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMscited by 2
  37. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  38. 2026When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Modelscited by 2

50 most cited of 68 All 68 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning
  2. 2024Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
  3. 2024Visual Hallucination: Definition, Quantification, and Prescriptive Remediations
  4. 2023Detecting and Preventing Hallucinations in Large Vision Language Models
  5. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
  6. 2024Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding
  7. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs
  8. 2025Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens