mlsanityData to 7 Oct 2026

MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

arXiv 2406.08772 ↗First posted 13 Jun 2024cs.CV cs.CLcited by 60

Not on the map. Why?

Abstract (arXiv)

Current multimodal misinformation detection (MMD) methods often assume a single source and type of forgery for each sample, which is insufficient for real-world scenarios where multiple forgery sources coexist. The lack of a benchmark for mixed-source misinformation has hindered progress in this field. To address this, we introduce MMFakeBench, the first comprehensive benchmark for mixed-source MMD. MMFakeBench includes 3 critical sources: textual veracity distortion, visual veracity distortion, and cross-modal consistency distortion, along with 12 sub-categories of misinformation forgery types. We further conduct an extensive evaluation of 6 prevalent detection methods and 15 Large Vision-Language Models (LVLMs) on MMFakeBench under a zero-shot setting. The results indicate that current methods struggle under this challenging and realistic mixed-source MMD setting. Additionally, we propose MMD-Agent, a novel approach to integrate the reasoning, action, and tool-use capabilities of LVLM agents, significantly enhancing accuracy and generalization. We believe this study will catalyze future research into more realistic mixed-source multimodal misinformation and provide a fair evaluation of misinformation detection methods.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 50 of its 64 references that are in the map. First posted on arXiv 13 Jun 2024.

Builds on

50 of 64 references.

References · 50

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2023Visual Instruction Tuningcited by 7,792
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  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
38 more
  1. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  2. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  3. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  4. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  5. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  6. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  7. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  8. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  9. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 548
  10. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  11. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  12. 2023PandaGPT: One Model To Instruction-Follow Them Allcited by 330
  13. 2018FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Mediacited by 281
  14. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  15. 2023DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Modelscited by 124
  16. 2020Visual News: Benchmark and Challenges in News Image Captioningcited by 121
  17. 2021NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Mediacited by 106
  18. 2022End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Modelscited by 105
  19. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  20. 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
  21. 2019A Richly Annotated Corpus for Different Tasks in Automated Fact-Checkingcited by 74
  22. 2024SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detectioncited by 73
  23. 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
  24. 2021Towards Few-Shot Fact-Checking via Perplexitycited by 63
  25. 2024CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputscited by 56
  26. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  27. 2019r/Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detectioncited by 53
  28. 2022Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generationcited by 41
  29. 2023COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairscited by 39
  30. 2024FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMscited by 38
  31. 2018Deep Multimodal Image-Repurposing Detectioncited by 31
  32. 2017Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Textcited by 28
  33. 2021COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learningcited by 26
  34. 2022Bootstrapping Multi-view Representations for Fake News Detectioncited by 25
  35. 2021FakeFlow: Fake News Detection by Modeling the Flow of Affective Informationcited by 20
  36. 2023InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Advisercited by 17
  37. 2020Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformationcited by 15
  38. 2024Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasonercited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 28; 2026: 22.

60 papers.

Sort:

By area:

  1. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 42
  2. 2025Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detectioncited by 34
  3. 2024Jailbreak Attacks and Defenses against Multimodal Generative Models: A Surveycited by 31
  4. 2024Exploring Large Language Models for Feature Selection: A Data-centric Perspectivecited by 27
  5. 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMscited by 25
  6. 2024Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?cited by 17
  7. 2025AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Webcited by 17
  8. 2024MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Modelscited by 15
  9. 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Modelscited by 13
  10. 2024Similarity over Factuality: Are we making progress on multimodal out-of-context misinformation detection?cited by 11
  11. 2025TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detectioncited by 10
  12. 2025RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checkingcited by 9
38 more
  1. 2025The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contextscited by 8
  2. 2025Truth over Tricks: Measuring and Mitigating Shortcut Learning in Misinformation Detectioncited by 8
  3. 2025M4FC: a Multimodal, Multilingual, Multicultural, Multitask Real-World Fact-Checking Datasetcited by 7
  4. 2025XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMscited by 6
  5. 2025Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detectioncited by 6
  6. 2026The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detectioncited by 6
  7. 2025Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Modelscited by 5
  8. 2026VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checkingcited by 5
  9. 2025HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claimscited by 4
  10. 2025T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Searchcited by 4
  11. 2025Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baselinecited by 4
  12. 2025Fit for Purpose? Deepfake Detection in the Real Worldcited by 4
  13. 2026All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detectioncited by 4
  14. 2026From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wildcited by 3
  15. 2026FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detectioncited by 3
  16. 2024MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detectioncited by 2
  17. 2025Evidence-Grounded Multimodal Misinformation Detection with Attention-Based GNNscited by 2
  18. 2025DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationalescited by 2
  19. 2026Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detectioncited by 2
  20. 2026LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detectioncited by 2
  21. 2024ViLBias: Detecting and Reasoning about Bias in Multimodal Contentcited by 1
  22. 2025Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Koreacited by 1
  23. 2025Latent Reconstruction from Generated Data for Multimodal Misinformation Detectioncited by 1
  24. 2025Effectiveness of Large Multimodal Models in Detecting Disinformation: Experimental Resultscited by 1
  25. 2025Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarkscited by 1
  26. 2025AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMscited by 1
  27. 2025A parameter-efficient three-branch architecture for multimodal misinformation detection with limited annotationscited by 1
  28. 2026GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?cited by 1
  29. 2026RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wildcited by 1
  30. 2026SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformationcited by 1
  31. 2024Deep Learning Technology for Face Forgery Detection: A Surveycited by 0
  32. 2024CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multi-modal Fake News Detectioncited by 0
  33. 2025Towards Explainable Bilingual Multimodal Misinformation Detection and Localizationcited by 0
  34. 2025MERIT: Modular Framework for Multimodal Misinformation Detection with Web-Grounded Reasoningcited by 0
  35. 2025Insight-A: Attribution-aware for Multimodal Misinformation Detectioncited by 0
  36. 2025RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wildcited by 0
  37. 2026PartisanLens: A Multilingual Dataset of Hyperpartisan and Conspiratorial Immigration Narratives in European Mediacited by 0
  38. 2026Multilingual, Multimodal Pipeline for Creating Authentic and Structured Fact-Checked Claim Datasetcited by 0

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detection
  2. 2024Multimodal Misinformation Detection using Large Vision-Language Models
  3. 2024LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation
  4. 2025VLDBench Evaluating Multimodal Disinformation with Regulatory Alignment
  5. 2025E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detection
  6. 2024Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs
  7. 2025DFBench: Benchmarking Deepfake Image Detection Capability of Large Multimodal Models
  8. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation