{"id":"https://openalex.org/W7140103192","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.52","title":"Scaling Data-Constrained Language Models with Synthetic Data","display_name":"Scaling Data-Constrained Language Models with Synthetic Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140103192","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.52"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.52","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.52","pdf_url":"https://aclanthology.org/2026.findings-eacl.52.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: EACL 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-eacl.52.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013141721","display_name":"Hirokazu Kiyomaru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirokazu Kiyomaru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130337102","display_name":"Yusuke Oda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Oda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130365436","display_name":"Takashi Kodama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Kodama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130333002","display_name":"Chaoran Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaoran Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130349544","display_name":"Daisuke Kawahara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daisuke Kawahara","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":0.2480849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1002","last_page":"1016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.326200008392334,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.326200008392334,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.11479999870061874,"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/T10028","display_name":"Topic Modeling","score":0.08749999850988388,"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/synthetic-data","display_name":"Synthetic data","score":0.476500004529953},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3815000057220459},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.37459999322891235},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.35359999537467957},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2962000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6230000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48890000581741333},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.52","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.52","pdf_url":"https://aclanthology.org/2026.findings-eacl.52.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.52","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.52","pdf_url":"https://aclanthology.org/2026.findings-eacl.52.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311508","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140103192.pdf","grobid_xml":"https://content.openalex.org/works/W7140103192.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"improve":[4],"with":[5,124],"more":[6,66],"training":[7],"data,":[8],"but":[9],"practical":[10],"limits":[11],"on":[12],"data":[13,30,87],"collection":[14],"increasingly":[15],"constrain":[16],"further":[17],"scaling.Advances":[18],"in":[19,47,53],"instruction-following":[20],"LLMs":[21,39,73],"have":[22],"enabled":[23],"controlled,":[24],"high-quality":[25],"text":[26,58,70],"generation,":[27],"making":[28],"synthetic":[29,90,106],"a":[31,48,61],"potential":[32],"remedy.However,":[33],"its":[34],"effectiveness":[35],"for":[36,45],"pre-training":[37],"non-English":[38],"remains":[40],"underexplored.We":[41],"study":[42],"this":[43],"question":[44],"Japanese":[46,56,78,91,96,107,127],"fixed":[49],"token":[50,120],"budget":[51,121],"setting":[52],"which":[54],"organic":[55,67,126],"Web":[57,69,97,102,128],"constitutes":[59],"only":[60],"small":[62],"share,":[63],"while":[64],"far":[65],"English":[68,101],"and":[71,99,112],"instructionfollowing":[72],"capable":[74],"of":[75],"generating":[76,89],"fluent":[77],"are":[79],"available.We":[80],"compare":[81],"three":[82],"strategies":[83],"to":[84],"fill":[85],"the":[86,94,114,118],"shortfall:":[88],"text,":[92,98],"repeating":[93],"limited":[95],"using":[100],"text.Experiments":[103],"show":[104],"that":[105],"corpora":[108],"outperform":[109],"both":[110],"baselines":[111],"approach":[113],"performance":[115],"achieved":[116],"when":[117],"entire":[119],"is":[122],"filled":[123],"additional":[125],"text.":[129],"1":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-24T00:00:00"}