{"id":3465,"date":"2026-06-27T13:24:35","date_gmt":"2026-06-27T11:24:35","guid":{"rendered":"https:\/\/hria.upb.ro\/?post_type=dt_portfolio&#038;p=3465"},"modified":"2026-06-27T13:24:35","modified_gmt":"2026-06-27T11:24:35","slug":"improving-romanian-llm-pretraining-data-using-diversity-and-quality-filtering","status":"publish","type":"dt_portfolio","link":"https:\/\/hria.upb.ro\/en\/eveniment\/improving-romanian-llm-pretraining-data-using-diversity-and-quality-filtering\/","title":{"rendered":"Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering"},"content":{"rendered":"<div class=\"wpb-content-wrapper\"><p>[vc_row][vc_column][vc_column_text css=&#8221;&#8221;]<\/p>\n<p style=\"text-align: justify;\"><strong>Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering<\/strong>. Vlad-Andrei Negoi\u021b\u0103, Mihai Masala and Traian Rebedea. In: Proceedings of the Second Workshop on Language Models for Low-Resource Languages (<a href=\"https:\/\/loreslm.github.io\/cfp\" target=\"_blank\" rel=\"noopener\">LoResLM 2 EACL 2026<\/a>), 24-29 March 2026, Rabat, Morocco, DOI: <a href=\"https:\/\/doi.org\/10.18653\/v1\/2026.loreslm-1.13\" target=\"_blank\" rel=\"noopener\">10.18653\/v1\/2026.loreslm-1.13<\/a>.<\/p>\n<p>[\/vc_column_text][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>[vc_row][vc_column][vc_column_text css=&#8221;&#8221;] Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering. Vlad-Andrei Negoi\u021b\u0103, Mihai Masala and Traian Rebedea. In: Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2 EACL 2026), 24-29 March 2026, Rabat, Morocco, DOI: 10.18653\/v1\/2026.loreslm-1.13. [\/vc_column_text][\/vc_column][\/vc_row]<\/p>\n","protected":false},"author":1,"featured_media":1997,"comment_status":"closed","ping_status":"closed","template":"","dt_portfolio_category":[35,34,51,37],"dt_portfolio_tags":[],"class_list":["post-3465","dt_portfolio","type-dt_portfolio","status-publish","has-post-thumbnail","hentry","dt_portfolio_category-conferinta","dt_portfolio_category-lucrari-stiintifice","dt_portfolio_category-sp_upb_conf","dt_portfolio_category-sp_upb","dt_portfolio_category-35","dt_portfolio_category-34","dt_portfolio_category-51","dt_portfolio_category-37","description-off"],"translation":{"provider":"WPGlobus","version":"3.0.2","language":"en","enabled_languages":["ro","en"],"languages":{"ro":{"title":true,"content":true,"excerpt":false},"en":{"title":false,"content":false,"excerpt":false}}},"_links":{"self":[{"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/dt_portfolio\/3465","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/dt_portfolio"}],"about":[{"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/types\/dt_portfolio"}],"author":[{"embeddable":true,"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/comments?post=3465"}],"version-history":[{"count":1,"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/dt_portfolio\/3465\/revisions"}],"predecessor-version":[{"id":3466,"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/dt_portfolio\/3465\/revisions\/3466"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/media\/1997"}],"wp:attachment":[{"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/media?parent=3465"}],"wp:term":[{"taxonomy":"dt_portfolio_category","embeddable":true,"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/dt_portfolio_category?post=3465"},{"taxonomy":"dt_portfolio_tags","embeddable":true,"href":"https:\/\/hria.upb.ro\/en\/wp-json\/wp\/v2\/dt_portfolio_tags?post=3465"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}