{"id":"https://openalex.org/W7166878630","doi":"https://doi.org/10.18653/v1/2026.acl-long.1262","title":"Demystifying Data Organization for Enhanced LLM Training","display_name":"Demystifying Data Organization for Enhanced LLM Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166878630","doi":"https://doi.org/10.18653/v1/2026.acl-long.1262"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1262","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1262","pdf_url":"https://aclanthology.org/2026.acl-long.1262.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.1262.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030897484","display_name":"Yalun Dai","orcid":"https://orcid.org/0009-0001-4260-4385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yalun Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139784534","display_name":"Yangyu Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyu Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139783294","display_name":"Tongshen Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongshen Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137319658","display_name":"Yonghan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonghan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838455","display_name":"Xin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719945","display_name":"Wenshan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenshan Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139802595","display_name":"Qihao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qihao Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139836816","display_name":"Hao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139757612","display_name":"Yuanyuan Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanyuan Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022468480","display_name":"Kim\u2013Hui Yap","orcid":"https://orcid.org/0000-0003-1933-4986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim-Hui Yap","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139786955","display_name":"Scarlett Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scarlett Li","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":0.86647516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27358","last_page":"27375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.11150000244379044,"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":0.11150000244379044,"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":0.11050000041723251,"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":0.06669999659061432,"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/training","display_name":"Training (meteorology)","score":0.49219998717308044},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3095000088214874},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.3025999963283539},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.27880001068115234}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4171999990940094},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3052999973297119},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3003000020980835},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C110354214","wikidata":"https://www.wikidata.org/wiki/Q6314146","display_name":"Engineering management","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1262","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1262","pdf_url":"https://aclanthology.org/2026.acl-long.1262.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.1262","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1262","pdf_url":"https://aclanthology.org/2026.acl-long.1262.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":0.7579511404037476,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166878630.pdf","grobid_xml":"https://content.openalex.org/works/W7166878630.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Yalun":[0],"Dai,":[1],"Yangyu":[2],"Huang,":[3],"Tongshen":[4],"Yang,":[5],"Yonghan":[6],"Wang,":[7],"Xin":[8],"Zhang,":[9],"Wenshan":[10],"Wu,":[11],"Qihao":[12],"Zhao,":[13],"Hao":[14],"Li,":[15],"Yuanyuan":[16],"Gao,":[17],"Kim-Hui":[18],"Yap,":[19],"Scarlett":[20],"Li.":[21],"Proceedings":[22],"of":[23,28],"the":[24,29],"64th":[25],"Annual":[26],"Meeting":[27],"Association":[30],"for":[31],"Computational":[32],"Linguistics":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2026.":[38]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
