mlsanityData to 7 Oct 2026

Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity

arXiv 2604.04692 ↗First posted 6 Apr 2026cs.CL cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Automated fact-checking is a crucial task that supports a responsible information ecosystem. While recent research has progressed from text-only to multimodal fact-checking, a prevailing assumption is that incorporating visual evidence universally improves verification accuracy. In this work, we challenge this assumption and show that the indiscriminate use of visual evidence can reduce accuracy. Building on this finding, we propose AMuFC, a modular fact-checking framework that employs two collaborative vision-language models with distinct roles to enable the adaptive use of visual evidence. Experimental results on three datasets, including WebFC, introduced in this study, demonstrate the effectiveness of adaptive visual evidence use in fact-checking.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 6 Apr 2026.

Builds on

36 of 58 references.

References · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  7. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  8. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  9. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  10. 2025Small Language Models are the Future of Agentic AIcited by 254
  11. 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
  12. 2021NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Mediacited by 106
24 more
  1. 2022End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Modelscited by 105
  2. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  3. 2019Fact-Checking Meets Fauxtography: Verifying Claims About Imagescited by 52
  4. 2020Language Models as Fact Checkers?cited by 51
  5. 2023Multimodal Automated Fact-Checking: A Surveycited by 51
  6. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 42
  7. 2020Detecting Cross-Modal Inconsistency to Defend Against Neural Fake Newscited by 41
  8. 2024FIRE: Fact-checking with Iterative Retrieval and Verificationcited by 39
  9. 2023Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checkingcited by 34
  10. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 28
  11. 2024MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexitycited by 28
  12. 2023Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generationcited by 25
  13. 2023ChartCheck: Explainable Fact-Checking over Real-World Chart Imagescited by 25
  14. 2025FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Modelscited by 19
  15. 2025AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Webcited by 17
  16. 2018The PS-Battles Dataset - an Image Collection for Image Manipulation Detectioncited by 16
  17. 2021Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformationcited by 16
  18. 2024MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checkingcited by 10
  19. 2024Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answeringcited by 10
  20. 2024Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategiescited by 10
  21. 2026VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checkingcited by 5
  22. 2025Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verificationcited by 4
  23. 2024How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Modelscited by 3
  24. 2025PASS-FC: Progressive and Adaptive Search Scheme for Fact Checking of Comprehensive Claimscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
  2. 2024Piecing It All Together: Verifying Multi-Hop Multimodal Claims
  3. 2026MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation
  4. 2024MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models
  5. 2025MuSciClaims: Multimodal Scientific Claim Verification
  6. 2025HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims
  7. 2025RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
  8. 2026Fact or Fake? Assessing the Role of Deepfake Detectors in Multimodal Misinformation Detection