{"id":32612,"date":"2025-04-03T13:45:05","date_gmt":"2025-04-03T11:45:05","guid":{"rendered":"https:\/\/opi.org.pl\/?post_type=opi_publication&#038;p=32612"},"modified":"2025-04-03T13:45:07","modified_gmt":"2025-04-03T11:45:07","slug":"a-review-of-the-challenges-with-massive-web-mined-corpora-used-in-large-language-models-pre-training","status":"publish","type":"opi_publication","link":"https:\/\/opi.org.pl\/en\/opi_publication\/a-review-of-the-challenges-with-massive-web-mined-corpora-used-in-large-language-models-pre-training\/","title":{"rendered":"A Review of the Challenges with Massive Web-Mined Corpora Used in Large Language Models Pre-training"},"content":{"rendered":"<p class=\"opi-publication-authors\">Micha\u0142 Pere\u0142kiewicz, Rafa\u0142 Po\u015bwiata<\/p><p class=\"opi-publication-where\"><span class=\"year\">2025<\/span> W: Artificial Intelligence and Soft Computing : 23rd International Conference, ICAISC 2024, Zakopane, Poland, June 16\u201320, 2024, Proceedings, Part III \/ Leszek Rutkowski, Rafa\u0142 Scherer, Marcin Korytkowski, Witold Pedrycz, Ryszard Tadeusiewicz, Jacek M. Zurada. - Cham : Springer. - s. 153-156<\/p><p class=\"opi-publication-conference\"> International Conference on Artificial Intelligence and Soft Computing [ICAISC], Zakopane, 16-20.06.2024<\/p><p class=\"opi-publication-url\"><a href=\"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-81596-6_14\" aria-label=\"A Review of the Challenges with Massive Web-Mined Corpora Used in Large Language Models Pre-training\" target=\"_blank\">https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-81596-6_14<\/a><\/p>","protected":false},"excerpt":{"rendered":"<p>Micha\u0142 Pere\u0142kiewicz, Rafa\u0142 Po\u015bwiata2025 W: Artificial Intelligence and Soft Computing : 23rd International Conference, ICAISC 2024, Zakopane, Poland, June 16\u201320, 2024, Proceedings, Part III \/ Leszek Rutkowski, Rafa\u0142 Scherer, Marcin Korytkowski, Witold Pedrycz, Ryszard Tadeusiewicz, Jacek M. Zurada. &#8211; Cham : Springer. &#8211; s. 153-156 International Conference on Artificial Intelligence and Soft Computing [ICAISC], Zakopane,&hellip;<\/p>\n","protected":false},"template":"","meta":{"_links_to":"","_links_to_target":""},"class_list":["post-32612","opi_publication","type-opi_publication","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/opi.org.pl\/en\/wp-json\/wp\/v2\/opi_publication\/32612","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/opi.org.pl\/en\/wp-json\/wp\/v2\/opi_publication"}],"about":[{"href":"https:\/\/opi.org.pl\/en\/wp-json\/wp\/v2\/types\/opi_publication"}],"wp:attachment":[{"href":"https:\/\/opi.org.pl\/en\/wp-json\/wp\/v2\/media?parent=32612"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}