Fine-grained and Dense Annotation of Czech Propaganda Using Large Language Models

Investor logo

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

SABOL Radoslav HORÁK Aleš

Year of publication 2025
Type Article in Proceedings
Conference Recent Advances in Slavonic Natural Language Processing, RASLAN 2025
MU Faculty or unit

Faculty of Informatics

Citation
web Proceedings of the Nineteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2025.
Keywords manipulative techniques; propaganda; detection; annotation; large language models; LLM; Czech
Attached files
Description WithinthepreviousprojectofCzechPropagandaDetectionthat aimed to recognize manipulative techniques in Czech news articles, the annotation was mostly limited to indicating the presence of a technique in a document. Inabout35%ofthedocuments,span-level evidence was also annotated, but only as a support for the document-level labels, resulting in a sparse coverage of the techniques. Thus, the resulting dataset has limitations for training and evaluating more fine-grained propaganda detection models. In this study, we examine the potential of large language models (LLMs) to generate dense span-level annotations of manipulative techniques in Czech news articles. We designed generation prompts tailored to each technique and experimented with several LLMs to produce annotations for a subset of the Czech Propaganda dataset. We present the details of the generation process, including the design of the prompts and the selection of models. We also evaluate the generated annotations both quantitatively and qualitatively, including a manual validation and comparison with human annotations.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.