@inproceedings{henriksson-etal-2025-finerweb, title = "{FinerWeb-10BT}: {Refining} Web Data with {LLM}-Based Line-Level Filtering", author = "Henriksson, Erik and Tarkka, Otto and Ginter, Filip", editor = "Johansson, Richard and Stymne, Sara", booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)", month = mar, year = "2025", address = "Tallinn, Estonia", publisher = "University of Tartu Library", url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.nodalida-1.27/", pages = "258--268", ISBN = "978-9908-53-109-0" }