mlsanityData to 14 Oct 2026

Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges

arXiv 2311.03287 ↗First posted 6 Nov 2023cs.LG cs.CL cs.CVcited by 131

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

Abstract (arXiv)

While GPT-4V(ision) impressively models both visual and textual information simultaneously, it's hallucination behavior has not been systematically assessed. To bridge this gap, we introduce a new benchmark, namely, the Bias and Interference Challenges in Visual Language Models (Bingo). This benchmark is designed to evaluate and shed light on the two common types of hallucinations in visual language models: bias and interference. Here, bias refers to the model's tendency to hallucinate certain types of responses, possibly due to imbalance in its training data. Interference pertains to scenarios where the judgment of GPT-4V(ision) can be disrupted due to how the text prompt is phrased or how the input image is presented. We identify a notable regional bias, whereby GPT-4V(ision) is better at interpreting Western images or images with English writing compared to images from other countries or containing text in other languages. Moreover, GPT-4V(ision) is vulnerable to leading questions and is often confused when interpreting multiple images together. Popular mitigation approaches, such as self-correction and chain-of-thought reasoning, are not effective in resolving these challenges. We also identified similar biases and interference vulnerabilities with LLaVA and Bard. Our results characterize the hallucination challenges in GPT-4V(ision) and state-of-the-art visual-language models, and highlight the need for new solutions. The Bingo benchmark is available at https://github.com/gzcch/Bingo.

Key facts. Cited by 131 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 23 of its 33 references that are in the map. First posted on arXiv 6 Nov 2023.

Builds on

23 of 33 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Models24 Oct
  2. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models23 Oct
  3. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models1 Oct
  4. 2023Evaluation and Analysis of Hallucination in Large Vision-Language Models29 Aug
  5. 2023Detecting and Preventing Hallucinations in Large Vision Language Models11 Aug
  6. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun
  7. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May

Other references · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  8. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  9. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  10. 2022Generating Sequences by Learning to Self-Correctcited by 277
  11. 2021Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Conceptscited by 256
  12. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matterscited by 222
4 more
  1. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 197
  2. 2023Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluationcited by 46
  3. 2023An Early Evaluation of GPT-4V(ision)cited by 31
  4. 2023Lost in Translation: When GPT-4V(ision) Can't See Eye to Eye with Text. A Vision-Language-Consistency Analysis of VLLMs and Beyondcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 70; 2025: 36; 2026: 16.

131 papers.

Sort:

By area:

  1. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  2. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 512
  3. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 388
  4. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 372
  5. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluationcited by 300
  6. 2024Rethinking Machine Unlearning for Large Language Modelscited by 257
  7. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 198
  8. 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaborationcited by 189
  9. 2024HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decodingcited by 174
  10. 2025PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understandingcited by 160
  11. 2025MMSearch-R1: Incentivizing LMMs to Searchcited by 124
  12. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
38 more
  1. 2023How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMscited by 108
  2. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  3. 2024Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequencescited by 94
  4. 2024VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Modelscited by 90
  5. 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Modelscited by 86
  6. 2024A Survey on Benchmarks of Multimodal Large Language Modelscited by 82
  7. 2024Calibrated Self-Rewarding Vision Language Modelscited by 78
  8. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 76
  9. 2023Multimodal Representation Learning by Alternating Unimodal Adaptationcited by 75
  10. 2024Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvementcited by 74
  11. 2024MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMscited by 72
  12. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 65
  13. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Modelscited by 64
  14. 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Modelscited by 53
  15. 2024Visual Agents as Fast and Slow Thinkerscited by 53
  16. 2024VHELM: A Holistic Evaluation of Vision Language Modelscited by 53
  17. 2024Machine Unlearning in Generative AI: A Surveycited by 49
  18. 2024Mitigating Object Hallucination via Concentric Causal Attentioncited by 49
  19. 2024How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Promptscited by 47
  20. 2024A Survey on Evaluation of Multimodal Large Language Modelscited by 46
  21. 2024PhD: A ChatGPT-Prompted Visual hallucination Evaluation Datasetcited by 45
  22. 2024MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videoscited by 43
  23. 2024Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation datacited by 39
  24. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  25. 2025Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoningcited by 36
  26. 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Modelscited by 34
  27. 2024LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Contentcited by 33
  28. 2024MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Modelscited by 33
  29. 2024HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoningcited by 32
  30. 2024AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrailscited by 31
  31. 2024How Far Are We From AGI: Are LLMs All We Need?cited by 31
  32. 2024Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Modelscited by 31
  33. 2024FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedbackcited by 30
  34. 2024Effectiveness Assessment of Recent Large Vision-Language Modelscited by 29
  35. 2025Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimizationcited by 29
  36. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  37. 2024A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applicationscited by 27
  38. 2024Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveycited by 27

50 most cited of 131 All 131 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Visual Hallucination: Definition, Quantification, and Prescriptive Remediations
  2. 2024Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations
  3. 2024MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context
  4. 2025Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models
  5. 2026Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM
  6. 2025Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model
  7. 2025A Survey of Multimodal Hallucination Evaluation and Detection
  8. 2024Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization