{"id":"https://openalex.org/W4412944731","doi":"https://doi.org/10.18653/v1/2025.acl-long.1163","title":"Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies","display_name":"Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944731","doi":"https://doi.org/10.18653/v1/2025.acl-long.1163"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1163","pdf_url":"https://aclanthology.org/2025.acl-long.1163.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1163.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101886933","display_name":"Zhengyu Chen","orcid":"https://orcid.org/0009-0003-8892-5699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420082","display_name":"Siqi Wang","orcid":"https://orcid.org/0000-0002-8807-640X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siqi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103046190","display_name":"Teng Xiao","orcid":"https://orcid.org/0000-0001-9180-1433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011309730","display_name":"Yudong Wang","orcid":"https://orcid.org/0000-0002-0156-1294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yudong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shiqi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiqi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101316434","display_name":"Xunliang Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunliang Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015879697","display_name":"Junxian He","orcid":"https://orcid.org/0009-0007-9559-6941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junxian He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100695181","display_name":"Jingang Wang","orcid":"https://orcid.org/0000-0002-2999-3371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingang Wang","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":17.0842,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99228604,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"23881","last_page":"23899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9613000154495239,"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":0.9430000185966492,"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/computer-science","display_name":"Computer science","score":0.7058533430099487},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6326873898506165},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5507614612579346},{"id":"https://openalex.org/keywords/scaling-law","display_name":"Scaling law","score":0.5141687393188477},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4771801233291626},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.45325997471809387},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45087385177612305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4404885470867157},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4118177890777588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39288562536239624},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.17001795768737793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1303149163722992},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.10386684536933899},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06761494278907776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058533430099487},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6326873898506165},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5507614612579346},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.5141687393188477},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4771801233291626},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.45325997471809387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45087385177612305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4404885470867157},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4118177890777588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39288562536239624},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17001795768737793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1303149163722992},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.10386684536933899},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06761494278907776},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1163","pdf_url":"https://aclanthology.org/2025.acl-long.1163.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167256","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167256","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1163","pdf_url":"https://aclanthology.org/2025.acl-long.1163.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944731.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2117748264","https://openalex.org/W4298190863","https://openalex.org/W2518229301","https://openalex.org/W2597205018","https://openalex.org/W2554072523","https://openalex.org/W1671671741","https://openalex.org/W2952002823","https://openalex.org/W2013329450","https://openalex.org/W3104909087","https://openalex.org/W2512421151"],"abstract_inverted_index":{"Zhengyu":[0],"Chen,":[1,9],"Siqi":[2],"Wang,":[3,7],"Teng":[4],"Xiao,":[5],"Yudong":[6],"Shiqi":[8],"Xunliang":[10],"Cai,":[11],"Junxian":[12],"He,":[13],"Jingang":[14],"Wang.":[15],"Proceedings":[16],"of":[17,22],"the":[18,23],"63rd":[19],"Annual":[20],"Meeting":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics":[27],"(Volume":[28],"1:":[29],"Long":[30],"Papers).":[31],"2025.":[32]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}
