mlsanityData to 14 Oct 2026

Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs

arXiv 2409.19656 ↗First posted 29 Sep 2024cs.CLcited by 13

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

also in 1 more
Abstract (arXiv)

Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies. However, the generalizability of detectors trained on synthetic data to real-world scenarios remains unclear due to the distribution gap. To address this, we propose learning from synthetic data for detecting real-world multimodal misinformation through two model-agnostic data selection methods that match synthetic and real-world data distributions. Experiments show that our method enhances the performance of a small MLLM (13B) on real-world fact-checking datasets, enabling it to even surpass GPT-4V~citeGPT-4V.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 48 of its 81 references that are in the map. First posted on arXiv 29 Sep 2024.

Builds on

48 of 81 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection5 Mar

Other references · 47

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  7. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  8. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  9. 2024Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMscited by 735
  10. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  11. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  12. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 614
35 more
  1. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 547
  2. 2024LESS: Selecting Influential Data for Targeted Instruction Tuningcited by 532
  3. 2023PandaGPT: One Model To Instruction-Follow Them Allcited by 334
  4. 2023Data Selection for Language Models via Importance Resamplingcited by 329
  5. 2023TRAK: Attributing Model Behavior at Scalecited by 283
  6. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 282
  7. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  8. 2024A Survey on Data Selection for Language Modelscited by 236
  9. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  10. 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
  11. 2020Visual News: Benchmark and Challenges in News Image Captioningcited by 121
  12. 2021NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Mediacited by 107
  13. 2022End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Modelscited by 107
  14. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 99
  15. 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
  16. 2023LAVA: Data Valuation without Pre-Specified Learning Algorithmscited by 69
  17. 2020SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Modelscited by 56
  18. 2023Multimodal Automated Fact-Checking: A Surveycited by 53
  19. 2023AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensicscited by 46
  20. 2023T-MARS: Improving Visual Representations by Circumventing Text Feature Learningcited by 43
  21. 2021KL Guided Domain Adaptationcited by 35
  22. 2020Multimodal Analytics for Real-world News using Measures of Cross-modal Entity Consistencycited by 33
  23. 2024Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMscited by 32
  24. 2018Deep Multimodal Image-Repurposing Detectioncited by 31
  25. 2017Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Textcited by 28
  26. 2024LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentationcited by 28
  27. 2024Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filterscited by 25
  28. 2023The Devil is in the Details: A Deep Dive into the Rabbit Hole of Data Filteringcited by 19
  29. 2023Data Valuation and Detections in Federated Learningcited by 17
  30. 2018The PS-Battles Dataset - an Image Collection for Image Manipulation Detectioncited by 16
  31. 2023Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusioncited by 15
  32. 2021Localize, Group, and Select: Boosting Text-VQA by Scene Text Modelingcited by 14
  33. 2023Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Groundingcited by 7
  34. 2024Private Wasserstein Distancecited by 4
  35. 2023Informative Data Selection with Uncertainty for Multi-modal Object Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 5.

13 papers.

Sort:

By area:

  1. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 43
  2. 2025AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Webcited by 18
  3. 2025XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMscited by 7
  4. 2024Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baselinecited by 6
  5. 2026The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detectioncited by 6
  6. 2025T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Searchcited by 4
  7. 2025E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detectioncited by 1
  8. 2025Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspectivecited by 1
  9. 2026Multimodal Claim Extraction for Fact-Checkingcited by 1
  10. 2026REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detectioncited by 1
  11. 2026SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformationcited by 1
  12. 2025From Veracity to Diffusion: Adressing Operational Challenges in Moving From Fake-News Detection to Information Disorderscited by 0
1 more
  1. 2026Latent Fact-Checking: Detecting Misinformation through Activation Engineeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims
  2. 2024Multimodal Misinformation Detection using Large Vision-Language Models
  3. 2024LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
  4. 2025MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection
  5. 2026Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detection
  6. 2026Can Multimodal Large Language Models Generate and Detect Multimodal Social Media Fake News?
  7. 2025Effectiveness of Large Multimodal Models in Detecting Disinformation: Experimental Results
  8. 2024Multimodal Large Language Models to Support Real-World Fact-Checking