{"id":"https://openalex.org/W4378474172","doi":"https://doi.org/10.48550/arxiv.2305.15212","title":"Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning","display_name":"Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4378474172","doi":"https://doi.org/10.48550/arxiv.2305.15212"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.15212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15212","pdf_url":"https://arxiv.org/pdf/2305.15212","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.15212","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023202249","display_name":"Zhen-Ru Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Zhen-Ru","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065907658","display_name":"Chuanqi Tan","orcid":"https://orcid.org/0000-0002-6676-3057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Chuanqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078053186","display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0002-9457-4552"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Haiyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373451","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1010-9678"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chengyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059743923","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0001-9207-8953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047856952","display_name":"Songfang Huang","orcid":"https://orcid.org/0000-0001-8084-0904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Songfang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023202249"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9970999956130981,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"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/prefix","display_name":"Prefix","score":0.9138280153274536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7896344661712646},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7453083992004395},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.6358243823051453},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5316112041473389},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47006019949913025},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45283034443855286},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.42714959383010864},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41889190673828125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22239753603935242},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16881802678108215},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07758742570877075},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06847134232521057},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06610801815986633}],"concepts":[{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.9138280153274536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896344661712646},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7453083992004395},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.6358243823051453},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5316112041473389},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47006019949913025},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45283034443855286},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.42714959383010864},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41889190673828125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22239753603935242},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16881802678108215},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07758742570877075},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06847134232521057},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06610801815986633},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.15212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15212","pdf_url":"https://arxiv.org/pdf/2305.15212","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.15212","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.15212","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.15212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15212","pdf_url":"https://arxiv.org/pdf/2305.15212","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378474172.pdf","grobid_xml":"https://content.openalex.org/works/W4378474172.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3023285645","https://openalex.org/W3037551068","https://openalex.org/W3023594376","https://openalex.org/W4287802662","https://openalex.org/W4385570973","https://openalex.org/W4385574003","https://openalex.org/W4308829884","https://openalex.org/W3154646238","https://openalex.org/W2899852118","https://openalex.org/W4309877123"],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"pre-trained":[2,31],"language":[3],"models":[4],"on":[5,38,55,122],"various":[6],"downstream":[7],"tasks":[8],"with":[9,28,117],"whole":[10],"parameters":[11,27],"is":[12],"prohibitively":[13],"expensive.":[14],"Hence,":[15],"Parameter-efficient":[16],"fine-tuning":[17,90],"has":[18],"attracted":[19],"attention":[20],"that":[21,58,73],"only":[22,42],"optimizes":[23,43],"a":[24,66,118,139],"few":[25],"task-specific":[26],"the":[29,56,59,74,85,89,104,123,129,136,143,148],"frozen":[30],"model.":[32],"In":[33,133],"this":[34],"work,":[35],"we":[36,71,96,141],"focus":[37],"prefix":[39,45,76,105],"tuning,":[40],"which":[41],"continuous":[44],"vectors":[46],"(i.e.":[47],"pseudo":[48],"tokens)":[49],"inserted":[50],"into":[51],"Transformer":[52],"layers.":[53],"Based":[54],"observation":[57],"learned":[60],"syntax":[61],"and":[62,93,113,125,145],"semantics":[63],"representation":[64],"varies":[65],"lot":[67],"at":[68],"different":[69],"layers,":[70],"argue":[72],"adaptive":[75],"will":[77],"be":[78],"further":[79],"tailored":[80],"to":[81,102],"each":[82],"layer":[83,115],"than":[84],"fixed":[86],"one,":[87],"enabling":[88],"more":[91],"effective":[92],"efficient.":[94],"Thus,":[95],"propose":[97],"Adaptive":[98],"Prefix":[99],"Tuning":[100],"(APT)":[101],"adjust":[103],"in":[106],"terms":[107],"of":[108,131,147],"both":[109],"fine-grained":[110],"token":[111],"level":[112,116],"coarse-grained":[114],"gate":[119,137],"mechanism.":[120],"Experiments":[121],"SuperGLUE":[124],"NER":[126],"datasets":[127],"show":[128],"effectiveness":[130,146],"APT.":[132],"addition,":[134],"taking":[135],"as":[138],"probing,":[140],"validate":[142],"efficiency":[144],"variable":[149],"prefix.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}