Fine-tuning LLMs with hierarchical prompting on a new intent-based propaganda taxonomy turns weak zero-shot performance into competitive results, especially on ambiguous low-agreement labels.
Includes WWII analogies, Hitler/SS references, burning people like Nazis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas
Fine-tuning LLMs with hierarchical prompting on a new intent-based propaganda taxonomy turns weak zero-shot performance into competitive results, especially on ambiguous low-agreement labels.