{"id":"https://openalex.org/W4385768040","doi":"https://doi.org/10.24963/ijcai.2023/455","title":"Efficient NLP Model Finetuning via Multistage Data Filtering","display_name":"Efficient NLP Model Finetuning via Multistage Data Filtering","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768040","doi":"https://doi.org/10.24963/ijcai.2023/455"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/455","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/455","pdf_url":"https://www.ijcai.org/proceedings/2023/0455.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0455.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107222587","display_name":"Xu Ouyang","orcid":"https://orcid.org/0000-0003-2852-5733"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Ouyang","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086616339","display_name":"Shahina Mohd Azam Ansari","orcid":"https://orcid.org/0000-0003-4229-6359"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahina Mohd Azam Ansari","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025585492","display_name":"Felix Xiaozhu Lin","orcid":"https://orcid.org/0000-0002-1615-6419"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Xiaozhu Lin","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085302513","display_name":"Yangfeng Ji","orcid":"https://orcid.org/0000-0002-7793-486X"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangfeng Ji","raw_affiliation_strings":["University of Virginia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4091","last_page":"4099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8728042244911194},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7551242113113403},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6921209096908569},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6236815452575684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5649138689041138},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5631970763206482},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5568615794181824},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5435916185379028},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5169567465782166},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4726606607437134},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45899608731269836},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.0784960687160492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8728042244911194},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7551242113113403},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6921209096908569},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6236815452575684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5649138689041138},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5631970763206482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5568615794181824},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5435916185379028},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5169567465782166},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4726606607437134},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45899608731269836},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0784960687160492},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/455","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/455","pdf_url":"https://www.ijcai.org/proceedings/2023/0455.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/455","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/455","pdf_url":"https://www.ijcai.org/proceedings/2023/0455.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1852190989","display_name":"Collaborative Research: CNS Core: Medium: Understanding and Strengthening Memory Security for Non-Volatile Memory","funder_award_id":"2106893","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2484545922","display_name":"CAREER: A Trustworthy and Verifiable Software Backplane for the Cloud Edge","funder_award_id":"2128725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3161045478","display_name":"SaTC: CORE: Small: Generalizing Adversarial Examples in Natural Language","funder_award_id":"2124538","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8345018822","display_name":"SPX: Write Once, Run on Anything: Verified, Tuned Accelerator Kernels from High Level Specifications","funder_award_id":"1919197","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768040.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1821462560","https://openalex.org/W1902934009","https://openalex.org/W1924689489","https://openalex.org/W2040870580","https://openalex.org/W2118020653","https://openalex.org/W2132984949","https://openalex.org/W2152551290","https://openalex.org/W2160208155","https://openalex.org/W2167706101","https://openalex.org/W2170240176","https://openalex.org/W2763421725","https://openalex.org/W2766164908","https://openalex.org/W2866343820","https://openalex.org/W2896457183","https://openalex.org/W2903158431","https://openalex.org/W2923014074","https://openalex.org/W2952902402","https://openalex.org/W2954732411","https://openalex.org/W2962945654","https://openalex.org/W2963122961","https://openalex.org/W2963809228","https://openalex.org/W2964303773","https://openalex.org/W2970106668","https://openalex.org/W2978017171","https://openalex.org/W2980708516","https://openalex.org/W2996428491","https://openalex.org/W3015982254","https://openalex.org/W3035204084","https://openalex.org/W3035608860","https://openalex.org/W3105966348","https://openalex.org/W3176211720","https://openalex.org/W3176828726","https://openalex.org/W3215408659","https://openalex.org/W4288026527","https://openalex.org/W4288335875","https://openalex.org/W4288358328","https://openalex.org/W4288618204","https://openalex.org/W4294583774","https://openalex.org/W4294635920","https://openalex.org/W4312832303"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W17155033","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"As":[0],"model":[1],"finetuning":[2,156],"is":[3,130,141,146,151,159],"central":[4],"to":[5,11,43,113,120,148],"the":[6,22,55,88,107,154],"modern":[7],"NLP,":[8],"we":[9,28,41],"set":[10,42,101],"maximize":[12],"its":[13],"efficiency.":[14],"Motivated":[15],"by":[16,111,118],"redundancy":[17],"in":[18,47,51,91],"training":[19,33,45,54,67,73,84,95,109,116,134,139],"examples":[20,46,110],"and":[21,115,150],"sheer":[23],"sizes":[24],"of":[25,102],"pretrained":[26],"models,":[27],"exploit":[29],"a":[30,48,66,77,92,99],"key":[31,59],"opportunity:":[32],"only":[34,123,143],"on":[35],"important":[36],"data.":[37],"To":[38],"this":[39],"end,":[40],"filter":[44],"streaming":[49],"fashion,":[50],"tandem":[52],"with":[53,153],"target":[56],"model.":[57],"Our":[58,128],"techniques":[60,90],"are":[61],"two:":[62],"(1)":[63],"automatically":[64],"determine":[65],"loss":[68],"threshold":[69],"for":[70,80,133],"skipping":[71,82],"backward":[72],"passes;":[74],"(2)":[75],"run":[76],"meta":[78],"predictor":[79],"further":[81],"forward":[83],"passes.":[85],"We":[86],"integrate":[87],"above":[89],"holistic,":[93],"three-stage":[94],"pro-":[96],"cess.":[97],"On":[98],"diverse":[100],"benchmarks,":[103],"our":[104],"method":[105,129],"reduces":[106],"required":[108],"up":[112,119],"5.3\u00d7":[114],"time":[117],"6.8\u00d7,":[121],"while":[122],"seeing":[124],"minor":[125],"accuracy":[126],"degradation.":[127],"effective":[131],"even":[132],"one":[135],"epoch,":[136],"where":[137],"each":[138],"example":[140],"encountered":[142],"once.":[144],"It":[145],"simple":[147],"implement":[149],"compatible":[152],"existing":[155],"techniques.":[157],"Code":[158],"available":[160],"at:":[161],"https://github.com/xo28/efficient-NLP-multistage-training":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}