mlsanityData to 7 Oct 2026

MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification

arXiv 2405.19186 ↗First posted 29 May 2024cs.CV cs.CL cs.LGcited by 13

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

Abstract (arXiv)

Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon referred to as hallucinations, remain an unsolved problem with regard to the trustworthiness of LVLMs. To address this problem, recent works proposed to incorporate computationally costly Large (Vision) Language Models in order to detect hallucinations on a sentence- or subsentence-level. In this work, we introduce MetaToken, a lightweight binary classifier to detect hallucinations on the token-level at negligible cost. Based on a statistical analysis, we reveal key factors of hallucinations in LVLMs. MetaToken can be applied to any open-source LVLM without any knowledge about ground truth data providing a calibrated detection of hallucinations. We evaluate our method on four state-of-the-art LVLMs demonstrating the effectiveness of our approach.

Key facts. Cited by 13 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 60 of its 74 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

60 of 74 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models18 Feb
  2. 2024EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models15 Feb
  3. 2024Unified Hallucination Detection for Multimodal Large Language Models5 Feb
  4. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  5. 2023Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites4 Dec
  6. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  7. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Models24 Oct
  8. 2023Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models9 Oct
  9. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models1 Oct
  10. 2023Evaluation and Analysis of Hallucination in Large Vision-Language Models29 Aug
  11. 2023Detecting and Preventing Hallucinations in Large Vision Language Models11 Aug
  12. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun
2 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May
  2. 2022Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training14 Oct

Other references · 46

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  8. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  9. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  10. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  11. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  12. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
34 more
  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  5. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  6. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  7. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  8. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
  9. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  10. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  11. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
  12. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  13. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  14. 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 820
  15. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 742
  16. 2018Object Hallucination in Image Captioningcited by 661
  17. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 482
  18. 2023MultiModal-GPT: A Vision and Language Model for Dialogue with Humanscited by 255
  19. 2022A Survey of Vision-Language Pre-Trained Modelscited by 177
  20. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 137
  21. 2018Neural Baby Talkcited by 107
  22. 2018Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilitiescited by 54
  23. 2024A Survey for Foundation Models in Autonomous Drivingcited by 51
  24. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 50
  25. 2023Visual Instruction Tuning towards General-Purpose Multimodal Model: A Surveycited by 28
  26. 2018Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probescited by 21
  27. 2019Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networkscited by 20
  28. 2019Uncertainty Measures and Prediction Quality Rating for the Semantic Segmentation of Nested Multi Resolution Street Scene Imagescited by 18
  29. 2020MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detectioncited by 18
  30. 2023Vision-Language Instruction Tuning: A Review and Analysiscited by 17
  31. 2020Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimatescited by 14
  32. 2020YOdar: Uncertainty-based Sensor Fusion for Vehicle Detection with Camera and Radar Sensorscited by 13
  33. 2023Simple Token-Level Confidence Improves Caption Correctnesscited by 11
  34. 2023Temporal Performance Prediction for Deep Convolutional Long Short-Term Memory Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 7.

13 papers.

Sort:

By area:

  1. 2025Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainabilitycited by 28
  2. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  3. 2025Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigationcited by 20
  4. 2025LanP: Rethinking the Impact of Language Priors in Large Vision-Language Modelscited by 14
  5. 2026VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneckcited by 8
  6. 2026Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMscited by 3
  7. 2026Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinationscited by 3
  8. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  9. 2025Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -cited by 1
  10. 2026Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generationcited by 0
  11. 2026HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Modelscited by 0
  12. 2026Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMscited by 0
1 more
  1. 2026UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models
  2. 2024Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
  3. 2026HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token
  4. 2026SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering
  5. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
  6. 2024From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
  7. 2026Scalable Token-Level Hallucination Detection in Large Language Models
  8. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering