{"id":"https://openalex.org/W7140142014","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.13","title":"Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering","display_name":"Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140142014","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.13"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.loreslm-1.13","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.13","pdf_url":"https://aclanthology.org/2026.loreslm-1.13.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.loreslm-1.13.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083571032","display_name":"Vlad Negoita","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vlad-Andrei Negoi\u021b\u0103","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075638103","display_name":"Mihai Masala","orcid":"https://orcid.org/0000-0003-3496-9058","observed_orcids":["https://orcid.org/0000-0003-3496-9058"]},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mihai Masala","raw_affiliation_strings":["National University of Science and Technology POLITEHNICA Bucharest , 313 Splaiul Independentei , 060042 , Bucharest , Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology POLITEHNICA Bucharest , 313 Splaiul Independentei , 060042 , Bucharest , Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077365712","display_name":"Traian Eugen Rebedea","orcid":"https://orcid.org/0000-0002-7255-5537","observed_orcids":["https://orcid.org/0000-0002-7255-5537"]},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Traian Rebedea","raw_affiliation_strings":["National University of Science and Technology POLITEHNICA Bucharest , 313 Splaiul Independentei , 060042 , Bucharest , Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Science and Technology POLITEHNICA Bucharest , 313 Splaiul Independentei , 060042 , Bucharest , Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9362,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95382182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.034699998795986176,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-model-pretraining","display_name":"large language model pretraining","score":0.8339999914169312},{"id":"https://openalex.org/keywords/training-data-quality","display_name":"training data quality","score":0.7160000205039978},{"id":"https://openalex.org/keywords/data-filtering","display_name":"data filtering","score":0.8759999871253967},{"id":"https://openalex.org/keywords/dataset-diversity","display_name":"data diversity","score":0.871999979019165},{"id":"https://openalex.org/keywords/romanian-language","display_name":"Romanian language","score":0.8830000162124634},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7699999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5579000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5065000057220459},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3310000002384186},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.loreslm-1.13","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.13","pdf_url":"https://aclanthology.org/2026.loreslm-1.13.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.01090","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01090","pdf_url":"https://arxiv.org/pdf/2511.01090","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.01090","doi":"https://doi.org/10.48550/arxiv.2511.01090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.01090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.loreslm-1.13","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.13","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.13","pdf_url":"https://aclanthology.org/2026.loreslm-1.13.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4414739080","display_name":null,"funder_award_id":"334906","funder_id":"https://openalex.org/F4320311068","funder_display_name":"Health Resources in Action"}],"funders":[{"id":"https://openalex.org/F4320311068","display_name":"Health Resources in Action","ror":"https://ror.org/01ctnwa22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140142014.pdf","grobid_xml":"https://content.openalex.org/works/W7140142014.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4400104753","https://openalex.org/W4397028940","https://openalex.org/W4416048071","https://openalex.org/W4415933221","https://openalex.org/W7221136570","https://openalex.org/W7137426356","https://openalex.org/W7134997660","https://openalex.org/W4391899422","https://openalex.org/W4386644265","https://openalex.org/W4416092168"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"recently":[5],"exploded":[6],"in":[7,22,99,103],"popularity,":[8],"often":[9],"matching":[10],"or":[11],"outperforming":[12],"human":[13],"abilities":[14],"on":[15,71],"many":[16],"tasks.One":[17],"of":[18,30,53,113],"the":[19,26,49,100,111],"key":[20],"factors":[21],"training":[23,66],"LLMs":[24],"is":[25,34],"availability":[27],"and":[28,51,57,81,105],"curation":[29],"high-quality":[31,41,92],"data.Data":[32],"quality":[33],"especially":[35],"crucial":[36],"for":[37],"underrepresented":[38],"languages,":[39],"where":[40],"corpora":[42,56],"are":[43,77],"scarce.In":[44],"this":[45],"work,":[46],"we":[47,58,76],"study":[48],"characteristics":[50],"coverage":[52],"Romanian":[54,74,104],"pretraining":[55,93,119],"examine":[59],"how":[60],"they":[61],"differ":[62],"from":[63],"English":[64,106],"data.By":[65],"a":[67],"lightweight":[68],"multitask":[69],"model":[70],"carefully":[72],"LLM-annotated":[73],"texts,":[75],"able":[78],"to":[79,90],"analyze":[80],"perform":[82],"multi-level":[83],"filtering":[84,114],"(e.g.,":[85],"educational":[86],"value,":[87],"topic,":[88],"format)":[89],"generate":[91],"datasets.Our":[94],"experiments":[95],"show":[96],"noteworthy":[97],"trends":[98],"topics":[101],"present":[102],"data,":[107],"while":[108],"also":[109],"proving":[110],"effectiveness":[112],"data":[115],"through":[116],"improved":[117],"LLM":[118],"performance":[120],"across":[121],"multiple":[122],"benchmarks.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}