@inproceedings{nikolaev-etal-2025-factdebug,
    title = "{F}act{D}ebug at {S}em{E}val-2025 Task 7: Hybrid Retrieval Pipeline for Identifying Previously Fact-Checked Claims Across Multiple Languages",
    author = "Nikolaev, Evgenii  and
      Bondarenko, Ivan  and
      Aushev, Islam  and
      Krikunov, Vasilii  and
      Glinskii, Andrei  and
      Konovalov, Vasily  and
      Belikova, Julia",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.284/",
    pages = "2190--2196",
    ISBN = "979-8-89176-273-2",
    abstract = "The proliferation of multilingual misinformation demands robust systems for crosslingual fact-checked claim retrieval. This paper addresses SemEval-2025 Shared Task 7, which challenges participants to retrieve fact-checks for social media posts across 14 languages, even when posts and fact-checks are in different languages. We propose a hybrid retrieval pipeline that combines sparse lexical matching (BM25, BGE-m3) and dense semantic retrieval (pretrained and fine-tuned BGE-m3) with dynamic fusion and curriculum-trained rerankers. Our system achieves 67.2{\%} crosslingual and 86.01{\%} monolingual accuracy on the Shared Task MultiClaim dataset."
}