@inproceedings{zou-etal-2025-empowering,
    title = "Empowering Persuasion Detection in {S}lavic Texts through Two-Stage Generative Reasoning",
    author = "Zou, Xin  and
      Wang, Chuhan  and
      Li, Dailin  and
      Wang, Yanan  and
      Wang, Jian  and
      Lin, Hongfei",
    editor = "Piskorski, Jakub  and
      P{\v{r}}ib{\'a}{\v{n}}, Pavel  and
      Nakov, Preslav  and
      Yangarber, Roman  and
      Marcinczuk, Michal",
    booktitle = "Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.bsnlp-1.20/",
    doi = "10.18653/v1/2025.bsnlp-1.20",
    pages = "177--182",
    ISBN = "978-1-959429-57-9",
    abstract = "This paper presents our submission to Subtask 2 (multi-label classification of persuasion techniques) of the Shared Task on Detection and Classification of Persuasion Techniques in Slavic Languages at SlavNLP 2025. Our method leverages a teacher{--}student framework based on large language models (LLMs): a Qwen3 32B teacher model generates natural language explanations for annotated persuasion techniques, and a Qwen2.5 32B student model is fine-tuned to replicate both the teacher{'}s rationales and the final label predictions. We train our models on the official shared task dataset, supplemented by annotated resources from SemEval 2023 Task 3 and CLEF 2024 Task 3 covering English, Russian, and Polish to improve cross-lingual robustness. Our final system ranks 4th on BG, SI, and HR, and 5th on PL in terms of micro-F1 score among all participating teams."
}