@inproceedings{benchert-etal-2025-caidas,
    title = "{CAIDAS} at {S}em{E}val-2025 Task 7: Enriching Sparse Datasets with {LLM}-Generated Content for Improved Information Retrieval",
    author = "Benchert, Dominik  and
      Me{\ss}linger, Severin  and
      Goller, Sven  and
      Kaiser, Jonas  and
      Pfister, Jan  and
      Hotho, Andreas",
    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-1.214/",
    pages = "1623--1638",
    ISBN = "979-8-89176-273-2",
    abstract = "The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs. We explored and analyzed two main approaches for generating synthetic posts. Either based on existing fact-checks or on existing posts. Our approach achieved an S@10 score of 89.53{\%} for the monolingual task and 74.48{\%} for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th)."
}