{"id":"https://openalex.org/W7166820521","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1021","title":"Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models","display_name":"Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166820521","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1021"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1021","pdf_url":"https://aclanthology.org/2026.findings-acl.1021.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1021.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139826089","display_name":"Xiaomeng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaomeng Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139786870","display_name":"Yixuan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139733568","display_name":"Haoze Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoze Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139786768","display_name":"Hao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Chen","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":"middle","author":{"id":"https://openalex.org/A5139722625","display_name":"Zhanming Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanming Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139840051","display_name":"Yiming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744405","display_name":"Haobo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haobo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139722930","display_name":"Junbo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhao","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":0.81024577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20406","last_page":"20418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.34619998931884766,"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":0.34619998931884766,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.10620000213384628,"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":0.10339999943971634,"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/natural-language","display_name":"Natural language","score":0.29330000281333923},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2831000089645386},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2741999924182892},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2700999975204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6287999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2678999900817871}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1021","pdf_url":"https://aclanthology.org/2026.findings-acl.1021.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1021","pdf_url":"https://aclanthology.org/2026.findings-acl.1021.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166820521.pdf","grobid_xml":"https://content.openalex.org/works/W7166820521.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,36,59,100,103,106,114,122,151],"rapid":[2],"progress":[3],"of":[4,35,63,86,113],"large":[5],"language":[6],"models":[7],"(LLMs),":[8],"aligning":[9],"a":[10,20,82,144],"general-purpose":[11],"model":[12],"with":[13],"downstream":[14],"tasks":[15],"through":[16],"fine-tuning":[17,42,131,152],"has":[18,29,134],"become":[19],"central":[21],"research":[22],"focus.Selecting":[23],"only":[24],"high-quality":[25],"examples":[26],"for":[27],"training":[28,57,64,67,115],"been":[30],"shown":[31],"to":[32,40,121],"be":[33],"one":[34],"most":[37],"effective":[38],"ways":[39],"improve":[41],"performance.However,":[43],"prior":[44],"work":[45,77],"concentrates":[46],"almost":[47],"exclusively":[48],"on":[49,91,99,147],"data":[50,55,65,87,96,104,148],"preprocessing:":[51],"filtering":[52],"and":[53,61,105,108,128],"cleaning":[54],"before":[56],"begins.While":[58],"order":[60,88,116],"composition":[62],"during":[66],"have":[68],"received":[69],"little":[70],"fine-grained":[71,83],"attention.To":[72],"fill":[73],"this":[74],"gap,":[75],"our":[76],"proposed":[78],"Fine-Grained":[79],"Order":[80],"Fine-Tuning,":[81],"scheduling":[84,112],"method":[85],"in":[89,117,150],"epochs.Drawing":[90],"curriculum-learning":[92],"principles,":[93],"FOT":[94,133],"defines":[95],"difficulty":[97],"based":[98],"relevance":[101],"between":[102],"model,":[107],"then":[109],"performs":[110],"dynamic":[111],"each":[118],"epoch":[119],"according":[120],"difficulty.On":[123],"both":[124],"largescale":[125],"continued":[126],"pre-training":[127],"small-scale":[129],"supervised":[130],"experiments,":[132],"achieved":[135],"an":[136],"average":[137],"2.4%":[138],"improvement":[139],"over":[140],"baselines.Our":[141],"study":[142],"offers":[143],"new":[145],"perspective":[146],"governance":[149],"phase.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}