{"id":"https://openalex.org/W7166881382","doi":"https://doi.org/10.18653/v1/2026.acl-long.1214","title":"Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training","display_name":"Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166881382","doi":"https://doi.org/10.18653/v1/2026.acl-long.1214"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1214","pdf_url":"https://aclanthology.org/2026.acl-long.1214.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 64th 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/2026.acl-long.1214.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139736396","display_name":"Changhao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhao Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139758323","display_name":"Ming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012794275","display_name":"Yifei Cao","orcid":"https://orcid.org/0009-0002-2444-942X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifei Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139782809","display_name":"Junjie Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784348","display_name":"Xiaoran Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoran Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139758494","display_name":"Shihan Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihan Dou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139764928","display_name":"Zhiheng Xi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiheng Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139806396","display_name":"Jiajun Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139788098","display_name":"Yi Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792994","display_name":"Yujiong Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujiong Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113207942","display_name":"Jingqi Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingqi Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139791085","display_name":"Baoyu Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baoyu Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809977","display_name":"Tao Gui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Gui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139758763","display_name":"Qi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139829847","display_name":"Xuanjing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","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":0.86987977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26377","last_page":"26396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3118000030517578,"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":0.3118000030517578,"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/T13629","display_name":"Text Readability and Simplification","score":0.18170000612735748,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.04659999907016754,"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/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.46970000863075256},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44940000772476196},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.44029998779296875},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.43130001425743103},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.30480000376701355},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.29249998927116394}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5325000286102295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5074999928474426},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4424000084400177},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44029998779296875},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30329999327659607},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2987567764","wikidata":"https://www.wikidata.org/wiki/Q125421","display_name":"Second language","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1214","pdf_url":"https://aclanthology.org/2026.acl-long.1214.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1214","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1214","pdf_url":"https://aclanthology.org/2026.acl-long.1214.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8446516394615173,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1187148928","display_name":null,"funder_award_id":"62376061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5542150374","display_name":null,"funder_award_id":"62476061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166881382.pdf","grobid_xml":"https://content.openalex.org/works/W7166881382.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Changhao":[0],"Jiang,":[1],"Ming":[2],"Zhang,":[3,27],"Yifei":[4],"Cao,":[5],"Junjie":[6],"Ye,":[7],"Xiaoran":[8],"Fan,":[9,23],"Shihan":[10],"Dou,":[11],"Zhiheng":[12],"Xi,":[13],"Jiajun":[14],"Sun,":[15],"Yi":[16],"Dong,":[17],"Yujiong":[18],"Shen,":[19],"Jingqi":[20],"Tong,":[21],"Baoyu":[22],"Tao":[24],"Gui,":[25],"Qi":[26],"Xuanjing":[28],"Huang.":[29],"Proceedings":[30],"of":[31,36],"the":[32,37],"64th":[33],"Annual":[34],"Meeting":[35],"Association":[38],"for":[39],"Computational":[40],"Linguistics":[41],"(Volume":[42],"1:":[43],"Long":[44],"Papers).":[45],"2026.":[46]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}