Researchers have introduced UkrMeme, a new dataset comprising 200 Ukrainian wartime memes annotated for persuasion techniques. This dataset, along with PTM-UA (a translated subset of the Propaganda 950 benchmark), is used to evaluate vision-language models (VLMs) in detecting persuasive elements within memes. The study compares zero-shot prompting across various input types and analyzes explanation methods like Layer-wise Relevance Propagation (LRP) to understand how VLMs identify persuasive cues. AI
IMPACT This research could lead to more sophisticated AI models for analyzing propaganda and persuasive content in multimodal formats.
RANK_REASON The cluster describes a new academic paper introducing a dataset and methodology for AI research. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- DagsHub
- Gotit.pub
- Hugging Face
- Layer-Wise Relevance Propagation: An Overview
- Propaganda 950
- PTM-UA
- ScienceCast
- UkrMeme
- Veronika Solopova
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
