{"id":"https://openalex.org/W7160872542","doi":"https://doi.org/10.48550/arxiv.2605.07454","title":"GRaSp: Automatic Example Optimization for In-Context Learning in Low-Data Tasks","display_name":"GRaSp: Automatic Example Optimization for In-Context Learning in Low-Data Tasks","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160872542","doi":"https://doi.org/10.48550/arxiv.2605.07454"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07454","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07454","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135864117","display_name":"Simen Bihaug-Fr\u00f8yland","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bihaug-Fr\u00f8yland, Simen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063325405","display_name":"Henrik Br\u00e5dland","orcid":"https://orcid.org/0000-0002-1601-8884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Br\u00e5dland, Henrik","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":false,"cited_by_count":0,"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":0.25870001316070557,"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":0.25870001316070557,"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":0.23420000076293945,"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":0.23260000348091125,"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/grasp","display_name":"GRASP","score":0.722599983215332},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5882999897003174},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5360000133514404},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.49410000443458557},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.4851999878883362},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4050999879837036},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.37470000982284546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779699981212616},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.722599983215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989999771118164},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5882999897003174},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5181000232696533},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.4851999878883362},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07454","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07454","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In-context":[0],"learning":[1],"enables":[2],"large":[3,51],"language":[4],"models":[5],"to":[6,8,17,68,93,101],"adapt":[7],"new":[9],"tasks,":[10],"but":[11,152],"their":[12],"performance":[13],"is":[14,24,165],"highly":[15],"sensitive":[16],"the":[18,70,74,80,96,106,149,162],"selected":[19],"examples.":[20],"Finding":[21],"effective":[22],"demonstrations":[23],"particularly":[25],"difficult":[26],"in":[27,161],"domain-specific,":[28],"low-data":[29],"settings":[30],"where":[31],"high-quality":[32],"examples":[33],"are":[34],"scarce.":[35],"We":[36,83,109],"propose":[37],"GRaSp,":[38],"a":[39,50,86],"three-stage":[40],"framework":[41,75],"for":[42,167],"automatic":[43],"in-context":[44,72],"example":[45],"optimization.":[46],"By":[47],"first":[48],"generating":[49],"synthetic":[52,119],"candidate":[53,122,163],"pool,":[54],"then":[55],"structuring":[56],"it":[57,92],"with":[58],"clustering":[59],"and":[60,63,120,129,142],"dimensionality":[61],"reduction,":[62],"finally":[64],"using":[65],"genetic":[66],"algorithms":[67],"find":[69],"optimal":[71],"examples,":[73],"shows":[76],"consistent":[77],"improvements":[78],"on":[79,112],"NER":[81],"task.":[82],"also":[84],"introduce":[85],"custom":[87],"diversity-adaptive":[88],"mutation":[89],"mechanism,":[90],"allowing":[91],"transition":[94],"from":[95],"initial":[97],"broad":[98],"inter-cluster":[99],"exploration":[100],"focused":[102],"intra-cluster":[103],"refinement":[104],"as":[105],"population":[107],"converges.":[108],"evaluate":[110],"GRaSp":[111,134],"financial":[113],"named":[114],"entity":[115],"recognition":[116],"(FiNER-139),":[117],"comparing":[118],"human-annotated":[121],"pools":[123],"across":[124],"pool":[125,164],"sizes":[126],"of":[127],"500":[128],"5000.":[130],"With":[131],"non-synthetic":[132],"data,":[133],"achieves":[135],"45.84%":[136],"micro-F1,":[137],"consistently":[138],"outperforming":[139],"both":[140],"zero-shot":[141],"random":[143,150],"few-shot":[144],"baselines.":[145],"Synthetic":[146],"data":[147],"matches":[148],"baseline":[151],"does":[153],"not":[154],"exceed":[155],"it,":[156],"suggesting":[157],"that":[158],"distributional":[159],"variety":[160],"critical":[166],"generalization.":[168]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-12T00:00:00"}