{"id":"https://openalex.org/W4383604682","doi":"https://doi.org/10.48550/arxiv.2307.02732","title":"Evaluating the Evaluators: Are Current Few-Shot Learning Benchmarks Fit for Purpose?","display_name":"Evaluating the Evaluators: Are Current Few-Shot Learning Benchmarks Fit for Purpose?","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4383604682","doi":"https://doi.org/10.48550/arxiv.2307.02732"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.02732","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02732","pdf_url":"https://arxiv.org/pdf/2307.02732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.02732","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100019299","display_name":"Lu\u00edsa Shimabucoro","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shimabucoro, Lu\u00edsa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087823932","display_name":"Timothy M. Hospedales","orcid":"https://orcid.org/0000-0003-4867-7486","observed_orcids":["https://orcid.org/0000-0003-4867-7486"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hospedales, Timothy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039741908","display_name":"Henry Gouk","orcid":"https://orcid.org/0000-0002-0924-2933","observed_orcids":["https://orcid.org/0000-0002-0924-2933"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gouk, Henry","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":true,"cited_by_count":4,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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":0.0005000000237487257,"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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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/few-shot-learning","display_name":"few-shot learning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/benchmark-evaluation","display_name":"benchmark evaluation","score":0.5690000057220459},{"id":"https://openalex.org/keywords/cross-validation","display_name":"cross-validation","score":0.7580000162124634},{"id":"https://openalex.org/keywords/bootstrap-method","display_name":"bootstrapping","score":0.953000009059906},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.9879999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088090419769287},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7039639949798584},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6323215961456299},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6227539777755737},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6179794669151306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5980417132377625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.581310510635376},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5711984038352966},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5108558535575867},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4964798092842102},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4924796521663666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2906738519668579},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.13195335865020752},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11941000819206238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09106957912445068},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07309448719024658},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.02732","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02732","pdf_url":"https://arxiv.org/pdf/2307.02732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.02732","doi":"https://doi.org/10.48550/arxiv.2307.02732","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.02732","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.02732","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02732","pdf_url":"https://arxiv.org/pdf/2307.02732","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383604682.pdf","grobid_xml":"https://content.openalex.org/works/W4383604682.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4226205323"],"related_works":["https://openalex.org/W7115433132","https://openalex.org/W3132000425","https://openalex.org/W3181168306","https://openalex.org/W3044305947","https://openalex.org/W2986715375","https://openalex.org/W3019510943","https://openalex.org/W3164972323","https://openalex.org/W7133320003","https://openalex.org/W7223153300","https://openalex.org/W3178814223"],"abstract_inverted_index":{"Numerous":[0],"benchmarks":[1,16,139],"for":[2,36,76,83,108,130,140],"Few-Shot":[3],"Learning":[4],"have":[5],"been":[6,44],"proposed":[7],"in":[8,39,70,146],"the":[9,25,49,65,71,81,84,105,111],"last":[10],"decade.":[11],"However":[12],"all":[13],"of":[14,27,67,86,90,102,113,126,157],"these":[15],"focus":[17],"on":[18,164],"performance":[19,68,112],"averaged":[20],"over":[21],"many":[22],"tasks,":[23],"and":[24,32,79],"question":[26],"how":[28,158],"to":[29],"reliably":[30],"evaluate":[31],"tune":[33],"models":[34],"trained":[35],"individual":[37,165],"tasks":[38],"this":[40],"regime":[41],"has":[42],"not":[43,144],"addressed.":[45],"This":[46],"paper":[47],"presents":[48],"first":[50],"investigation":[51],"into":[52],"task-level":[53],"evaluation":[54],"--":[55],"a":[56,61,99,114,123,148,154],"fundamental":[57],"step":[58],"when":[59],"deploying":[60],"model.":[62],"We":[63,94],"measure":[64],"accuracy":[66],"estimators":[69],"few-shot":[72,141],"setting,":[73],"consider":[74],"strategies":[75],"model":[77,131],"selection,":[78],"examine":[80],"reasons":[82],"failure":[85],"evaluators":[87],"usually":[88],"thought":[89],"as":[91],"being":[92],"robust.":[93],"conclude":[95],"that":[96,137,150],"cross-validation":[97],"with":[98,122],"low":[100],"number":[101,125],"folds":[103,127],"is":[104,128],"best":[106],"choice":[107],"directly":[109],"estimating":[110],"model,":[115],"whereas":[116],"using":[117],"bootstrapping":[118],"or":[119],"cross":[120],"validation":[121],"large":[124],"better":[129],"selection":[132],"purposes.":[133],"Overall,":[134],"we":[135],"find":[136],"existing":[138],"learning":[142],"are":[143],"designed":[145],"such":[147],"way":[149],"one":[151],"can":[152,161],"get":[153],"reliable":[155],"picture":[156],"effectively":[159],"methods":[160],"be":[162],"used":[163],"tasks.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-07-08T00:00:00"}