{"id":"https://openalex.org/W4416036704","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.544","title":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","display_name":"Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036704","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.544"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.544","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.544","pdf_url":"https://aclanthology.org/2025.emnlp-main.544.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.544.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085966366","display_name":"Feiyang Kang","orcid":"https://orcid.org/0009-0001-8390-6662"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Feiyang Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031627270","display_name":"Newsha Ardalani","orcid":"https://orcid.org/0000-0002-9975-4819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Newsha Ardalani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002457261","display_name":"Michael Kuchnik","orcid":"https://orcid.org/0000-0002-0805-1828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Kuchnik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119844652","display_name":"Youssef Emad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youssef Emad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031013766","display_name":"Mostafa Elhoushi","orcid":"https://orcid.org/0000-0001-6172-4510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mostafa Elhoushi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074059458","display_name":"Saumitra SenGupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shubhabrata Sengupta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013045755","display_name":"Ramya Raghavendra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramya Raghavendra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032275274","display_name":"Ruoxi Jia","orcid":"https://orcid.org/0000-0001-9662-9556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruoxi Jia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028220093","display_name":"Carole-Jean Wu","orcid":"https://orcid.org/0000-0002-9032-7239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carole-Jean Wu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5085966366"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17540367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10750","last_page":"10769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.29190000891685486,"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":0.29190000891685486,"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":0.0689999982714653,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0658000037074089,"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":0.48890000581741333},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3752000033855438},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.28600001335144043},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.2842000126838684},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2799000144004822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5267999768257141},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24950000643730164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.544","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.544","pdf_url":"https://aclanthology.org/2025.emnlp-main.544.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.544","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.544","pdf_url":"https://aclanthology.org/2025.emnlp-main.544.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1126860111","display_name":null,"funder_award_id":"IIS-2312794","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2639095588","display_name":"Collaborative Research: RI: Small: Foundations of Few-Round Active Learning","funder_award_id":"2313130","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G625317779","display_name":"CAREER: Data Valuation in the Wild: Theories, Algorithms, and Applications","funder_award_id":"2239622","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036704.pdf","grobid_xml":"https://content.openalex.org/works/W4416036704.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Feiyang":[0],"Kang,":[1],"Newsha":[2],"Ardalani,":[3],"Michael":[4],"Kuchnik,":[5],"Youssef":[6],"Emad,":[7],"Mostafa":[8],"Elhoushi,":[9],"Shubhabrata":[10],"Sengupta,":[11],"Shang-Wen":[12],"Li,":[13],"Ramya":[14],"Raghavendra,":[15],"Ruoxi":[16],"Jia,":[17],"Carole-Jean":[18],"Wu.":[19],"Proceedings":[20],"of":[21],"the":[22],"2025":[23],"Conference":[24],"on":[25],"Empirical":[26],"Methods":[27],"in":[28],"Natural":[29],"Language":[30],"Processing.":[31],"2025.":[32]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}