{"id":"https://openalex.org/W4416034901","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.741","title":"SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity","display_name":"SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034901","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.741"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.741","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.741","pdf_url":"https://aclanthology.org/2025.findings-emnlp.741.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.741.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049134021","display_name":"Xiangyu Xi","orcid":"https://orcid.org/0000-0001-5211-2563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Deyang Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deyang Kong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628536","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-5357-3246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101852855","display_name":"Jiawei Yang","orcid":"https://orcid.org/0000-0003-0148-9728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101886930","display_name":"Zhengyu Chen","orcid":"https://orcid.org/0000-0002-1895-7842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695184","display_name":"Jingang Wang","orcid":"https://orcid.org/0000-0002-7889-1881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingang Wang","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/A5101435571","display_name":"Shikun Zhang","orcid":"https://orcid.org/0000-0002-8576-2674"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shikun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448687","display_name":"Wei Ye","orcid":"https://orcid.org/0000-0002-3514-1626"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Ye","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":0.43472764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13736","last_page":"13758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9620000123977661,"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":0.9620000123977661,"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/T13398","display_name":"Data Analysis with R","score":0.004699999932199717,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.003000000026077032,"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/mixing","display_name":"Mixing (physics)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.49720001220703125},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.3720000088214874},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2815000116825104}],"concepts":[{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.49720001220703125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.460099995136261},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.4074000120162964},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.741","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.741","pdf_url":"https://aclanthology.org/2025.findings-emnlp.741.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.741","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.741","pdf_url":"https://aclanthology.org/2025.findings-emnlp.741.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034901.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}