{"id":"https://openalex.org/W7126410686","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.11","title":"How Does In-Context Learning Help Prompt Tuning?","display_name":"How Does In-Context Learning Help Prompt Tuning?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126410686","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.11"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.11","pdf_url":"https://aclanthology.org/2024.findings-eacl.11.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.11.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101134209","display_name":"Simeng Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simeng Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124656051","display_name":"Yang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037853792","display_name":"Dan Iter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Iter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124629519","display_name":"Chenguang Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenguang Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082767919","display_name":"Mohit Iyyer","orcid":"https://orcid.org/0000-0001-7340-0804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohit Iyyer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6052,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69708302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10918","display_name":"Memory Processes and Influences","score":0.10589999705553055,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10918","display_name":"Memory Processes and Influences","score":0.10589999705553055,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.09960000216960907,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05249999836087227,"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/task","display_name":"Task (project management)","score":0.6840999722480774},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.583299994468689},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5218999981880188},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.49230000376701355},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.43540000915527344},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4296000003814697},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.3790000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106999754905701},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6840999722480774},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.49230000376701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42579999566078186},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3790000081062317},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.11","pdf_url":"https://aclanthology.org/2024.findings-eacl.11.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.11","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.11","pdf_url":"https://aclanthology.org/2024.findings-eacl.11.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1339228928","display_name":"RI: Medium: Tree-Structured Self-Supervised Modeling for Natural Language","funder_award_id":"1955567","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2601536509","display_name":"CAREER: Building Creative Writing Assistants for Machine-in-the-Loop Storytelling","funder_award_id":"2046248","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126410686.pdf","grobid_xml":"https://content.openalex.org/works/W7126410686.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"language":[2,56,79,133],"models":[3],"is":[4,163],"becoming":[5],"ever":[6],"more":[7],"impractical":[8],"due":[9],"to":[10,34,51,151,155,159],"their":[11],"rapidlygrowing":[12],"scale.This":[13],"motivates":[14],"the":[15,47,52,118,148,156],"use":[16],"of":[17,31,46,86,120,201],"parameter-efficient":[18,214],"adaptation":[19,215],"methods":[20,88],"such":[21],"as":[22],"prompt":[23,67,83,114],"tuning":[24,115],"(PT),":[25],"which":[26,44,70],"adds":[27],"a":[28,77,187,202,212,218],"small":[29],"number":[30],"tunable":[32],"embeddings":[33],"an":[35],"otherwise":[36],"frozen":[37],"model,":[38],"and":[39,109,123,144,165,172],"in-context":[40,111,149,199],"learning":[41],"(ICL),":[42],"in":[43,54,145],"demonstrations":[45],"task":[48,190],"are":[49],"provided":[50],"model":[53],"natural":[55,78],"without":[57],"any":[58],"additional":[59],"training.Recently,":[60],"Singhal":[61],"et":[62],"al.":[63],"(2022)":[64],"propose":[65],"\"instruction":[66],"tuning\"":[68],"(IPT),":[69],"combines":[71],"PT":[72,162,171,192],"with":[73,81,98,130,198],"ICL":[74,173],"by":[75,116],"concatenating":[76],"demonstration":[80,150],"learned":[82,185],"embeddings.While":[84],"all":[85,180],"these":[87],"have":[89],"proven":[90],"effective":[91],"on":[92,125,210],"different":[93,203],"tasks,":[94],"how":[95,110],"they":[96],"interact":[97],"each":[99],"other":[100],"remains":[101],"unexplored.In":[102],"this":[103],"paper,":[104],"we":[105],"empirically":[106],"study":[107],"when":[108,196],"examples":[112,200],"improve":[113],"measuring":[117],"effectiveness":[119],"ICL,":[121],"PT,":[122,143],"IPT":[124,138],"five":[126,181],"text":[127],"generation":[128],"tasks":[129],"multiple":[131],"base":[132],"models.We":[134],"observe":[135],"that":[136],"(1)":[137],"does":[139],"not":[140],"always":[141],"outperform":[142],"fact":[146],"requires":[147],"be":[152],"semantically":[153],"similar":[154],"test":[157],"input":[158],"yield":[160],"improvements;(2)":[161],"unstable":[164],"exhibits":[166],"high":[167],"variance,":[168],"but":[169],"combining":[170],"(into":[174],"IPT)":[175],"consistently":[176],"reduces":[177],"variance":[178],"across":[179],"tasks;":[182],"and(3)":[183],"prompts":[184],"for":[186,217],"specific":[188],"source":[189],"via":[191],"exhibit":[193],"positive":[194],"transfer":[195],"paired":[197],"target":[204],"task.Our":[205],"results":[206],"offer":[207],"actionable":[208],"insights":[209],"choosing":[211],"suitable":[213],"method":[216],"given":[219],"task.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}