{"slug": "propasafe-hybrid-a-text-based-hybrid-propaganda-detection-tool", "title": "Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection Tool", "summary": "A new arXiv paper, 2610.33464v1, introduces Propasafe-Hybrid, a sentence-level propaganda detection system that pairs a fine-tuned transformer classifier with LLM-based technique classification to identify, label and explain specific propaganda strategies. Propasafe-Hybrid outputs highlighted sentences, technique assignments and concise rationales, and uses a cost-aware pre-filtering stage that forwards only high-likelihood sentences to LLMs to reduce token usage while preserving the decision logic. The authors present the design as improving the explainability, efficiency and practical usability of sentence-level propaganda detection in real-world news environments.", "body_md": "arXiv:2610.33464v1 Announce Type: new \nAbstract: Propagandistic content increasingly circulates through online news and social media, where readers often encounter it with limited scrutiny, highlighting the need for reliable and fine-grained detection. This paper introduces Propasafe-Hybrid, a sentence-level system that integrates a fine-tuned transformer classifier with LLM-based technique classification to identify, label, and explain specific propaganda strategies. The pipeline generates actionable outputs, including highlighted sentences, technique assignments, and concise rationales, so users can immediately understand why a sentence was flagged and how each label was determined. To control inference cost, Propasafe-Hybrid employs a cost-aware pre-filtering stage that forwards only high-likelihood sentences to LLMs, reducing token usage while preserving the underlying decision logic. Together, these design choices enhance the explainability, efficiency, and practical usability of sentence-level propaganda detection in real-world news environments.", "url": "https://wpnews.pro/news/propasafe-hybrid-a-text-based-hybrid-propaganda-detection-tool", "canonical_source": "https://www.machinebrief.com/news/propasafe-hybrid-a-text-based-hybrid-propaganda-detection-to-rnth", "published_at": "2026-10-27 04:00:00+00:00", "updated_at": "2026-10-27 04:42:00.478836+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "natural-language-processing", "ai-research"], "entities": ["Propasafe-Hybrid", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/propasafe-hybrid-a-text-based-hybrid-propaganda-detection-tool", "markdown": "https://wpnews.pro/news/propasafe-hybrid-a-text-based-hybrid-propaganda-detection-tool.md", "text": "https://wpnews.pro/news/propasafe-hybrid-a-text-based-hybrid-propaganda-detection-tool.txt", "jsonld": "https://wpnews.pro/news/propasafe-hybrid-a-text-based-hybrid-propaganda-detection-tool.jsonld"}}