Large Language Models and Provenance Metadata for Determining the Relevance of Images and Videos in News Stories

Tomas Peterka, Matyas Bohacek
2/13/2025
cs.CLcs.CVcs.CY

No official code found. Best implementation: maty-bohacek/media-relevance-in-news-stories (0 stars, last commit 2025-02-22).

Abstract

The most effective misinformation campaigns are multimodal, often combining text with images and videos taken out of context -- or fabricating them entirely -- to support a given narrative. Contemporary methods for detecting misinformation, whether in deepfakes or text articles, often miss the interplay between multiple modalities. Built around a large language model, the system proposed in this paper addresses these challenges. It analyzes both the article's text and the provenance metadata of included images and videos to determine whether they are relevant. We open-source the system prototype and interactive web interface.

View on arXivView PDF

Code Implementations(1)

maty-bohacek/media-relevance-in-news-storiesCommunity63%

Official Implementation of the 'Large Language Models and Provenance Metadata for Determining the Relevance of Images and Videos in News Stories' arXiv pre-print

00PythonJan 7, 20251 years ago

Similar Papers

Dataset of News Articles with Provenance Metadata for Media Relevance Assessment

85% match2025

ViClaim: A Multilingual Multilabel Dataset for Automatic Claim Detection in Videos

82% match2025

VMID: A Multimodal Fusion LLM Framework for Detecting and Identifying Misinformation of Short Videos

82% match2024

Multimodal Misinformation Detection using Large Vision-Language Models

82% match1 repo12024

MultiCaption: Detecting disinformation using multilingual visual claims

82% match2 repos2026

Correcting misinformation on social media with a large language model

82% match1 repo82024

Cite this paper

@article{peterka2025large,
  title  = {Large Language Models and Provenance Metadata for Determining the Relevance of Images and Videos in News Stories},
  author = {Tomas Peterka and Matyas Bohacek},
  year   = {2025},
  eprint = {2502.09689},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.09689v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.09689.svg)](https://codeofpaper.com/paper/2502.09689)

Discussion