mlsanityData to 7 Oct 2026

SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection

arXiv 2403.03170 ↗First posted 5 Mar 2024cs.MM cs.AI cs.CLcited by 73

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

Abstract (arXiv)

Misinformation is a prevalent societal issue due to its potential high risks. Out-of-context (OOC) misinformation, where authentic images are repurposed with false text, is one of the easiest and most effective ways to mislead audiences. Current methods focus on assessing image-text consistency but lack convincing explanations for their judgments, which is essential for debunking misinformation. While Multimodal Large Language Models (MLLMs) have rich knowledge and innate capability for visual reasoning and explanation generation, they still lack sophistication in understanding and discovering the subtle crossmodal differences. In this paper, we introduce SNIFFER, a novel multimodal large language model specifically engineered for OOC misinformation detection and explanation. SNIFFER employs two-stage instruction tuning on InstructBLIP. The first stage refines the model's concept alignment of generic objects with news-domain entities and the second stage leverages language-only GPT-4 generated OOC-specific instruction data to fine-tune the model's discriminatory powers. Enhanced by external tools and retrieval, SNIFFER not only detects inconsistencies between text and image but also utilizes external knowledge for contextual verification. Our experiments show that SNIFFER surpasses the original MLLM by over 40% and outperforms state-of-the-art methods in detection accuracy. SNIFFER also provides accurate and persuasive explanations as validated by quantitative and human evaluations.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 38 of its 59 references that are in the map. First posted on arXiv 5 Mar 2024.

Builds on

38 of 59 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model15 Apr

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  6. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  8. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  10. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  11. 2017Decoupled Weight Decay Regularizationcited by 1,722
  12. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,291
25 more
  1. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  2. 2023A Survey on Multimodal Large Language Modelscited by 898
  3. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  4. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 548
  5. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  6. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 231
  7. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Modelscited by 223
  8. 2020Visual News: Benchmark and Challenges in News Image Captioningcited by 121
  9. 2021NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Mediacited by 106
  10. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  11. 2021Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resourcescited by 71
  12. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  13. 2019Fact-Checking Meets Fauxtography: Verifying Claims About Imagescited by 52
  14. 2019Exploiting Multi-domain Visual Information for Fake News Detectioncited by 48
  15. 2021Improving Fake News Detection by Using an Entity-enhanced Framework to Fuse Diverse Multimodal Cluescited by 48
  16. 2019The Role of User Profile for Fake News Detectioncited by 41
  17. 2022FakeSV: A Multimodal Benchmark with Rich Social Context for Fake News Detection on Short Video Platformscited by 41
  18. 2023VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Biascited by 37
  19. 2020Multimodal Analytics for Real-world News using Measures of Cross-modal Entity Consistencycited by 33
  20. 2018Deep Multimodal Image-Repurposing Detectioncited by 31
  21. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  22. 2017Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Textcited by 28
  23. 2023Synthetic Misinformers: Generating and Combating Multimodal Misinformationcited by 23
  24. 2023RED-DOT: Multimodal Fact-checking via Relevant Evidence Detectioncited by 18
  25. 2019AIRD: Adversarial Learning Framework for Image Repurposing Detectioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 44; 2026: 18.

73 papers.

Sort:

By area:

  1. 2024MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMscited by 60
  2. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 42
  3. 2025Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedbackcited by 27
  4. 2025Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategiescited by 16
  5. 2025COVE: COntext and VEracity prediction for out-of-context imagescited by 14
  6. 2025Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoningcited by 14
  7. 2024Multimodal Large Language Models to Support Real-World Fact-Checkingcited by 13
  8. 2024Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMscited by 13
  9. 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Modelscited by 13
  10. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Modelscited by 13
  11. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  12. 2024Similarity over Factuality: Are we making progress on multimodal out-of-context misinformation detection?cited by 11
38 more
  1. 2024Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detectioncited by 11
  2. 2025TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detectioncited by 10
  3. 2024Customized large language models can outperform Community Notes in correcting misinformationcited by 9
  4. 2025VLDBench Evaluating Multimodal Disinformation with Regulatory Alignmentcited by 8
  5. 2025E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detectioncited by 6
  6. 2025CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detectioncited by 6
  7. 2025The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Paperscited by 6
  8. 2025XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMscited by 6
  9. 2025Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detectioncited by 6
  10. 2026The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detectioncited by 6
  11. 2025Verifying Cross-modal Entity Consistency in News using Vision-language Modelscited by 5
  12. 2025Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Modelscited by 5
  13. 2025ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validationcited by 5
  14. 2024Fake News Detection: Comparative Evaluation of BERT-like Models and Large Language Models with Generative AI-Annotated Datacited by 4
  15. 2025Multimodal Inverse Attention Network with Intrinsic Discriminant Feature Exploitation for Fake News Detectioncited by 4
  16. 2025T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Searchcited by 4
  17. 2025ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Modelscited by 4
  18. 2025MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Mediacited by 4
  19. 2024Learning Domain-Invariant Features for Out-of-Context News Detectioncited by 3
  20. 2024"Image, Tell me your story!" Predicting the original meta-context of visual misinformationcited by 3
  21. 2025EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrievalcited by 3
  22. 2025DataPuzzle: Breaking Free from the Hallucinated Promise of LLMs in Data Analysiscited by 3
  23. 2025Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understandingcited by 3
  24. 2026What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previewscited by 3
  25. 2026From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wildcited by 3
  26. 2025Evidence-Grounded Multimodal Misinformation Detection with Attention-Based GNNscited by 2
  27. 2025Multi-MLLM Knowledge Distillation for Out-of-Context News Detectioncited by 2
  28. 2025Towards LLM-Centric Multimodal Fusion: A Survey on Integration Strategies and Techniquescited by 2
  29. 2025"Humor, Art, or Misinformation?": A Multimodal Dataset for Intent-Aware Synthetic Image Detectioncited by 2
  30. 2025A New Dataset and Benchmark for Grounding Multimodal Misinformationcited by 2
  31. 2025Latent Reconstruction from Generated Data for Multimodal Misinformation Detectioncited by 1
  32. 2025Effectiveness of Large Multimodal Models in Detecting Disinformation: Experimental Resultscited by 1
  33. 2025Out-of-Context Misinformation Detection via Variational Domain-Invariant Learning with Test-Time Trainingcited by 1
  34. 2025A parameter-efficient three-branch architecture for multimodal misinformation detection with limited annotationscited by 1
  35. 2026Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detectioncited by 1
  36. 2026RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wildcited by 1
  37. 2026From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videoscited by 1
  38. 2024CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multi-modal Fake News Detectioncited by 0

50 most cited of 73 All 73 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025HiEAG: Evidence-Augmented Generation for Out-of-Context Misinformation Detection
  2. 2024Multimodal Misinformation Detection using Large Vision-Language Models
  3. 2024LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation
  4. 2025DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales
  5. 2024Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection
  6. 2025Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline
  7. 2025MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection
  8. 2024Leveraging Chat-Based Large Vision Language Models for Multimodal Out-Of-Context Detection