{"id":"https://openalex.org/W4401863877","doi":"https://doi.org/10.1145/3637528.3671905","title":"MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning","display_name":"MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863877","doi":"https://doi.org/10.1145/3637528.3671905"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671905","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671905","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671905","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671905","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049731366","display_name":"Sanchit Sinha","orcid":"https://orcid.org/0000-0003-2650-0612"},"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":true,"raw_author_name":"Sanchit Sinha","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084729155","display_name":"Yuguang Yue","orcid":"https://orcid.org/0000-0001-9771-3557"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuguang Yue","raw_affiliation_strings":["Amazon AGI, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AGI, New York, NY, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103820833","display_name":"Victor Soto","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Soto","raw_affiliation_strings":["Amazon AGI, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AGI, New York, NY, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111301003","display_name":"Mayank Kulkarni","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayank Kulkarni","raw_affiliation_strings":["Amazon AGI, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AGI, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103532576","display_name":"Jianhua Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianhua Lu","raw_affiliation_strings":["Amazon AGI, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AGI, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013588572","display_name":"Aidong Zhang","orcid":"https://orcid.org/0000-0001-9723-3246"},"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":"Aidong Zhang","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049731366"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":3.1276,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92617507,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2711","last_page":"2720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9991999864578247,"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":0.996999979019165,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9650999903678894,"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/training","display_name":"Training (meteorology)","score":0.6902651190757751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6802680492401123},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6431338787078857},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.4466184675693512},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4209586977958679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4032916724681854},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14072981476783752},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.09661829471588135},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09043213725090027},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07979810237884521}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6902651190757751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802680492401123},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6431338787078857},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.4466184675693512},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4209586977958679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032916724681854},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14072981476783752},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09661829471588135},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09043213725090027},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07979810237884521},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671905","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671905","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671905","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671905","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671905","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671905","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401863877.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2747329762","https://openalex.org/W3099655892","https://openalex.org/W3152515526","https://openalex.org/W3156470785","https://openalex.org/W3167554296","https://openalex.org/W3192405822","https://openalex.org/W3205058818","https://openalex.org/W3210277894","https://openalex.org/W4221143046","https://openalex.org/W4285189120","https://openalex.org/W4385573261","https://openalex.org/W4385573777"],"related_works":["https://openalex.org/W2349222429","https://openalex.org/W1993394192","https://openalex.org/W3117430770","https://openalex.org/W2116230991","https://openalex.org/W2590751808","https://openalex.org/W1972377868","https://openalex.org/W2132709506","https://openalex.org/W2186895195","https://openalex.org/W2151995366","https://openalex.org/W2388933862"],"abstract_inverted_index":{"Adapting":[0],"large":[1],"language":[2],"models":[3,200],"(LLMs)":[4],"to":[5,27,80,117],"unseen":[6,28,118,128,160],"tasks":[7,113],"with":[8,150,194,202],"incontext":[9],"training":[10,154],"samples":[11],"without":[12],"fine-tuning":[13,60],"remains":[14],"an":[15,122,163,180],"important":[16],"research":[17],"problem.":[18],"To":[19],"learn":[20,102],"a":[21,47,64,82,94,134],"robust":[22],"LLM":[23],"that":[24,106,144,199],"adapts":[25,116],"well":[26,110],"tasks,":[29,175],"multiple":[30],"meta-training":[31,43,54,98,206],"approaches":[32,55],"have":[33],"been":[34],"proposed":[35],"such":[36],"as":[37],"MetaICL":[38],"and":[39,61,159,177],"MetaICT,":[40],"which":[41,100],"involve":[42],"pre-trained":[44],"LLMs":[45],"on":[46,63,111,127,138,156],"wide":[48],"variety":[49],"of":[50,68,86,125,153,165,172,174],"diverse":[51],"tasks.":[52,69,119],"These":[53],"essentially":[56],"perform":[57],"in-context":[58],"multi-task":[59],"evaluate":[62],"disjointed":[65,112],"test":[66],"set":[67,85],"Even":[70],"though":[71],"they":[72],"achieve":[73],"impressive":[74],"performance,":[75],"their":[76],"goal":[77],"is":[78],"never":[79],"compute":[81],"truly":[83,103],"general":[84],"parameters.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91,142,168],"propose":[92],"MAML-en-LLM,":[93],"novel":[95],"method":[96],"for":[97],"LLMs,":[99],"can":[101],"generalizable":[104],"parameters":[105],"not":[107],"only":[108],"performs":[109],"but":[114],"also":[115],"We":[120],"see":[121],"average":[123,164],"increase":[124],"2%":[126],"domains":[129,161],"in":[130,148,184],"the":[131,170],"performance":[132],"while":[133],"massive":[135],"4%":[136],"improvement":[137],"adaptation":[139],"performance.":[140],"Furthermore,":[141],"demonstrate":[143,198],"MAML-en-LLM":[145,203],"outperforms":[146],"baselines":[147],"settings":[149,192,197],"limited":[151],"amount":[152],"data":[155,196],"both":[157],"seen":[158],"by":[162],"2%.":[166],"Finally,":[167],"discuss":[169],"effects":[171],"type":[173],"optimizers":[176],"task":[178,191],"complexity,":[179],"avenue":[181],"barely":[182],"explored":[183],"metatraining":[185],"literature.":[186],"Exhaustive":[187],"experiments":[188],"across":[189],"7":[190],"along":[193],"two":[195],"trained":[201],"outperform":[204],"SOTA":[205],"approaches.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}