{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:54:36Z","timestamp":1772934876737,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401532","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"5462-5471","source":"Crossref","is-referenced-by-count":0,"title":["XDoGE: Multilingual Data Reweighting to Enhance Language Inclusivity in LLMs"],"prefix":"10.1109","author":[{"given":"I\u00f1aki","family":"Lacunza","sequence":"first","affiliation":[{"name":"Barcelona Supercomputing Center,Language Technologies Lab,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 Javier","family":"Saiz","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center,Language Technologies Lab,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Shvets","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center,Language Technologies Lab,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aitor","family":"Gonzalez-Agirre","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center,Language Technologies Lab,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0711-0029","authenticated-orcid":false,"given":"Marta","family":"Villegas","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center,Language Technologies Lab,Barcelona,Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The LLaMA 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref2","article-title":"Nemotron-4 340B technical report","volume":"abs\/2406.11704","author":"Adler","year":"2024","journal-title":"CoRR"},{"key":"ref3","article-title":"Qwen2 technical report","volume":"abs\/2407.10671","author":"Yang","year":"2024","journal-title":"CoRR"},{"key":"ref4","article-title":"Yi: Open foundation models by 01.AI","volume":"abs\/2403.04652","author":"Young","year":"2024","journal-title":"CoRR"},{"key":"ref5","article-title":"BLOOM: A 176B-parameter open-access multilingual language model","author":"Le","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Mixtral of experts","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2025.02.260"},{"key":"ref8","first-page":"12895","article-title":"DOGE: Domain reweighting with generalization estimation","volume-title":"Proc. 41st Int. Conf. Machine Learning (ICML\u201924)","author":"Fan","year":"2024"},{"key":"ref9","article-title":"Unimax: Fairer and more effective language sampling for large-scale multilingual pretraining","author":"Chung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.837"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70563-2_6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.49"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3059"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1432"},{"key":"ref15","article-title":"Distributionally robust neural networks","volume-title":"Int. Conf. Learning Representations","author":"Sagawa","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.845"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.560"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.mrl-1.19"},{"key":"ref19","article-title":"The FineWeb datasets: Decanting the web for the finest text data at scale","author":"Penedo","year":"2024","journal-title":"NeurIPS Datasets and Benchmarks Track"},{"key":"ref20","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Salamandra technical report","author":"Gonzalez-Agirre","year":"2025","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.63317\/395bxjhot8he"},{"key":"ref24","first-page":"1049110519","article-title":"Iberobench: A benchmark for LLM evaluation in Iberian languages","volume-title":"Proc. 31st Int. Conf. Comput. Linguistics","author":"Baucells","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref26","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deeplo-1.10"},{"key":"ref28","article-title":"Training compute-optimal large language models","volume-title":"Proc. 36th Int. Conf. Neural Information Processing Systems (NeurIPS \u201922)","author":"Hoffmann","year":"2022"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401532.pdf?arnumber=11401532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:19:14Z","timestamp":1772867954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401532","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}