{"id":"https://openalex.org/W7137883268","doi":"https://doi.org/10.1609/aaai.v40i38.40512","title":"Better Datasets Start from RefineLab: Automatic Optimization for High-Quality Dataset Refinement","display_name":"Better Datasets Start from RefineLab: Automatic Optimization for High-Quality Dataset Refinement","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137883268","doi":"https://doi.org/10.1609/aaai.v40i38.40512"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i38.40512","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40512","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i38.40512","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129691240","display_name":"Xiaonan Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaonan Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129687654","display_name":"Yue Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129695233","display_name":"Ping He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129743593","display_name":"Xiangliang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangliang Zhang","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"32374","last_page":"32382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5759000182151794,"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":0.5759000182151794,"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":0.10980000346899033,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.07880000025033951,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6829000115394592},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5960000157356262},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5846999883651733},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5681999921798706},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4106000065803528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8677999973297119},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5825999975204468},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42559999227523804},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.27790001034736633}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i38.40512","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40512","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i38.40512","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40512","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High\u2011quality":[0],"Question\u2013Answer":[1],"(QA)":[2],"datasets":[3,16,35,60,183],"are":[4],"foundational":[5],"for":[6,206],"reliable":[7],"Large":[8],"Language":[9],"Model":[10],"(LLM)":[11],"evaluation,":[12],"yet":[13],"even":[14],"expert\u2011crafted":[15],"exhibit":[17],"persistent":[18],"gaps":[19],"in":[20,32],"domain":[21],"coverage,":[22,185],"misaligned":[23],"difficulty":[24,186],"distributions,":[25],"and":[26,77,89,134,138,190],"factual":[27,188],"inconsistencies.":[28],"The":[29],"recent":[30],"surge":[31],"generative":[33],"model-powered":[34],"has":[36],"compounded":[37],"these":[38],"quality":[39,72,101,132,167],"challenges.":[40],"In":[41,91],"this":[42],"work,":[43],"we":[44],"introduce":[45],"RefineLab,":[46],"the":[47,100,124,171],"first":[48],"LLM\u2011driven":[49],"framework":[50],"that":[51,158,176],"automatically":[52],"refines":[53],"raw":[54],"QA":[55,103,148],"textual":[56],"data":[57],"into":[58],"high-quality":[59],"under":[61],"a":[62,68,82,95,114,127,135,195],"controllable":[63],"token\u2011budget":[64],"constraint.":[65,173],"RefineLab":[66,93,120,177,193],"takes":[67,121],"set":[69,115,129],"of":[70,102,116,130],"target":[71,131],"attributes":[73],"as":[74,105,107,122],"refinement":[75,118,141,161],"objectives":[76],"performs":[78],"selective":[79],"edits":[80],"within":[81],"predefined":[83],"token":[84,136],"budget":[85,172],"to":[86,146,163,170,199],"ensure":[87],"practicality":[88],"efficiency.":[90],"essence,":[92],"addresses":[94],"constrained":[96],"optimization":[97],"problem:":[98],"improving":[99],"samples":[104],"much":[106],"possible":[108],"while":[109,168],"respecting":[110],"resource":[111],"limitations.":[112],"With":[113],"available":[117],"operations,":[119],"input":[123],"original":[125],"dataset,":[126],"specified":[128],"dimensions,":[133],"budget,":[137],"determines":[139],"which":[140],"operations":[142],"should":[143],"be":[144],"applied":[145],"each":[147],"sample.":[149],"This":[150],"process":[151],"is":[152],"guided":[153],"by":[154],"an":[155],"assignment":[156],"module":[157],"selects":[159],"optimal":[160],"strategies":[162],"maximize":[164],"overall":[165],"dataset":[166,201],"adhering":[169],"Experiments":[174],"demonstrate":[175],"consistently":[178],"narrows":[179],"divergence":[180],"from":[181],"expert":[182],"across":[184],"alignment,":[187],"fidelity,":[189],"distractor":[191],"quality.":[192],"pioneers":[194],"scalable,":[196],"customizable":[197],"path":[198],"reproducible":[200],"design,":[202],"with":[203],"broad":[204],"implications":[205],"LLM":[207],"evaluation.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}