@inproceedings{gili-etal-2024-veryfit,
    title = "{V}eryf{IT} - Benchmark of Fact-Checked Claims for {I}talian: A {CALAMITA} Challenge",
    author = "Gili, Jacopo  and
      Patti, Viviana  and
      Passaro, Lucia  and
      Caselli, Tommaso",
    editor = "Dell'Orletta, Felice  and
      Lenci, Alessandro  and
      Montemagni, Simonetta  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
    month = dec,
    year = "2024",
    address = "Pisa, Italy",
    publisher = "CEUR Workshop Proceedings",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.clicit-1.123/",
    pages = "1116--1124",
    ISBN = "979-12-210-7060-6",
    abstract = "Achieving factual accuracy is a known pending issue for language models. Their design centered around the interactive component of user interaction and the extensive use of {\textquotedblleft}spontaneous{\textquotedblright} training data, has made them highly adept at conversational tasks but not fully reliable in terms of factual correctness. VeryfIT addresses this issue by evaluating the in-memory factual knowledge of language models on data written by professional fact-checkers, posing it as a true or false question.Topics of the statements vary but most are in specific domains related to the Italian government, policies, and social issues. The task presents several challenges: extracting statements from segments of speeches, determining appropriate contextual relevance both temporally and factually, and ultimately verifying the accuracy of the statements."
}