mlsanityData to 7 Oct 2026

Multimodal Fake News Video Explanation: Dataset, Analysis and Evaluation

arXiv 2501.08514 ↗First posted 15 Jan 2025cs.CV cs.MMcited by 1

Not on the map. Why?

Abstract (arXiv)

Multimodal fake news videos are difficult to interpret because they require comprehensive consideration of the correlation and consistency between multiple modes. Existing methods deal with fake news videos as a classification problem, but it's not clear why news videos are identified as fake. Without proper explanation, the end user may not understand the underlying meaning of the falsehood. Therefore, we propose a new problem - Fake news video Explanation (FNVE) - given a multimodal news post containing a video and title, our goal is to generate natural language explanations to reveal the falsity of the news video. To that end, we developed FakeVE, a new dataset of 2,672 fake news video posts that can definitively explain four real-life fake news video aspects. In order to understand the characteristics of fake news video explanation, we conducted an exploratory analysis of FakeVE from different perspectives. In addition, we propose a Multimodal Relation Graph Transformer (MRGT) based on the architecture of multimodal Transformer to benchmark FakeVE. The empirical results show that the results of the various benchmarks (adopted by FakeVE) are convincing and provide a detailed analysis of the differences in explanation generation of the benchmark models.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 15 Jan 2025.

Builds on

18 of 39 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  6. 2017Decoupled Weight Decay Regularizationcited by 1,722
  7. 2016Generating Visual Explanationscited by 156
  8. 2021e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Taskscited by 84
  9. 2024Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdomcited by 49
  10. 2022FakeSV: A Multimodal Benchmark with Rich Social Context for Fake News Detection on Short Video Platformscited by 41
  11. 2023Text with Knowledge Graph Augmented Transformer for Video Captioningcited by 27
  12. 2024FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Processcited by 25
6 more
  1. 2023Neighborhood Contrastive Transformer for Change Captioningcited by 16
  2. 2023COVID-VTS: Fact Extraction and Verification on Short Video Platformscited by 15
  3. 2023Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusioncited by 15
  4. 2021Multi-Modal Semantic Inconsistency Detection in Social Media News Postscited by 10
  5. 2023HAAV: Hierarchical Aggregation of Augmented Views for Image Captioningcited by 10
  6. 2023The Challenges of Studying Misinformation on Video-Sharing Platforms During Crises and Mass-Convergence Eventscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memescited by 0