{"id":"https://openalex.org/W7166818335","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1707","title":"A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT","display_name":"A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166818335","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1707"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1707","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1707","pdf_url":"https://aclanthology.org/2026.findings-acl.1707.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1707.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139797142","display_name":"Louis Est\u00e8ve","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louis Est\u00e8ve","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139813450","display_name":"Christophe Servan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Servan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113752501","display_name":"Thomas Lavergne","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Lavergne","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139834588","display_name":"Agata Savary","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agata Savary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92617908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34168","last_page":"34181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14242","display_name":"Nutrition, Health, and Society Studies","score":0.09799999743700027,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T14242","display_name":"Nutrition, Health, and Society Studies","score":0.09799999743700027,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12066","display_name":"Obesity and Health Practices","score":0.0885000005364418,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10866","display_name":"Nutritional Studies and Diet","score":0.08060000091791153,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5573999881744385},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.32659998536109924},{"id":"https://openalex.org/keywords/dietary-diversity","display_name":"Dietary diversity","score":0.2865000069141388},{"id":"https://openalex.org/keywords/ethnic-group","display_name":"Ethnic group","score":0.273499995470047},{"id":"https://openalex.org/keywords/indigenous","display_name":"Indigenous","score":0.2696000039577484}],"concepts":[{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5573999881744385},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.4011000096797943},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.325300008058548},{"id":"https://openalex.org/C3018403216","wikidata":"https://www.wikidata.org/wiki/Q108898813","display_name":"Dietary diversity","level":4,"score":0.2865000069141388},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C55958113","wikidata":"https://www.wikidata.org/wiki/Q169480","display_name":"Indigenous","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C45355965","wikidata":"https://www.wikidata.org/wiki/Q1643441","display_name":"Socioeconomics","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1707","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1707","pdf_url":"https://aclanthology.org/2026.findings-acl.1707.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1707","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1707","pdf_url":"https://aclanthology.org/2026.findings-acl.1707.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7062739133834839,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166818335.pdf","grobid_xml":"https://content.openalex.org/works/W7166818335.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diversity":[0],"has":[1],"been":[2],"gaining":[3],"interest":[4],"in":[5,9,46,140],"the":[6,12,38,50,71,109,122,130,143],"NLP":[7],"community":[8],"recent":[10],"years.At":[11],"same":[13,110],"time,":[14],"state-of-the-art":[15],"transformer":[16],"models":[17,78,99],"such":[18],"as":[19],"ModernBERT":[20],"use":[21,70],"very":[22],"large":[23],"pre-training":[24,55,123],"datasets,":[25],"which":[26],"are":[27],"driven":[28],"by":[29,33,125,133],"size":[30],"rather":[31],"than":[32,161],"diversity.This":[34],"summons":[35],"to":[36,74,127,135,154],"investigate":[37],"impact":[39],"of":[40,53,93,105,146],"diversity":[41,159],"on":[42,79,90,101],"pre-training.We":[43],"do":[44],"so":[45],"this":[47],"study,":[48],"with":[49,81,98,108,158,162],"express":[51],"intent":[52],"reducing":[54],"dataset":[56,124],"size,":[57,107],"while":[58,137],"retaining":[59],"at":[60],"least":[61],"comparable":[62],"performance.We":[63],"compare":[64,96],"diversity-driven":[65,118],"sampling":[66,119,160],"algorithms,":[67],"and":[68,87,117,129],"we":[69],"best":[72],"one":[73],"pre-train":[75],"several":[76],"Modern-BERT":[77],"French":[80,94],"a":[82,91],"fixed":[83],"compute":[84,111],"budget.We":[85,112],"fine-tune":[86],"evaluate":[88],"them":[89,97],"variety":[92],"benchmarks.We":[95],"pre-trained":[100],"randomly":[102],"sampled":[103],"data":[104],"commensurate":[106],"find":[113],"that":[114],"both":[115],"random":[116,163],"may":[120],"reduce":[121],"up":[126,134,153],"94%":[128],"pretraining":[131],"time":[132],"73%":[136],"maintaining":[138],"performance.Moreover,":[139],"some":[141],"tasks,":[142],"inherent":[144],"quality":[145],"models,":[147],"estimated":[148],"via":[149],"headonly":[150],"fine-tuning,":[151],"is":[152],"10":[155],"points":[156],"higher":[157],"sampling.1":[164],"34168":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
