{"id":"https://openalex.org/W7128809283","doi":"https://doi.org/10.48550/arxiv.2602.11863","title":"In-Context Function Learning in Large Language Models","display_name":"In-Context Function Learning in Large Language Models","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128809283","doi":"https://doi.org/10.48550/arxiv.2602.11863"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.11863","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.11863","pdf_url":"https://arxiv.org/pdf/2602.11863","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/2602.11863","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092048108","display_name":"Elif Akata","orcid":"https://orcid.org/0009-0001-2016-7671","observed_orcids":["https://orcid.org/0009-0001-2016-7671"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Akata, Elif","raw_affiliation_strings":["University of T\u00fcbingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036818549","display_name":"Konstantinos Voudouris","orcid":"https://orcid.org/0000-0001-8453-3557","observed_orcids":["https://orcid.org/0000-0001-8453-3557"]},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Voudouris, Konstantinos","raw_affiliation_strings":["Helmholtz Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz Munich","institution_ids":["https://openalex.org/I3018134672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010706885","display_name":"Vincent Fortuin","orcid":"https://orcid.org/0000-0002-0640-2671","observed_orcids":["https://orcid.org/0000-0002-0640-2671"]},"institutions":[{"id":"https://openalex.org/I4387153582","display_name":"University of Technology Nuremberg","ror":"https://ror.org/02sv65x64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4387153582"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fortuin, Vincent","raw_affiliation_strings":["University of Technology Nuremberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Nuremberg","institution_ids":["https://openalex.org/I4387153582"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101768980","display_name":"Eric Schulz","orcid":"https://orcid.org/0000-0003-3088-0371","observed_orcids":["https://orcid.org/0000-0003-3088-0371"]},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schulz, Eric","raw_affiliation_strings":["Helmholtz Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz Munich","institution_ids":["https://openalex.org/I3018134672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.6586999893188477,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.6586999893188477,"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/T10028","display_name":"Topic Modeling","score":0.12630000710487366,"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":0.09910000115633011,"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/in-context-learning","display_name":"in-context learning","score":0.9779999852180481},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8960000276565552},{"id":"https://openalex.org/keywords/gaussian-processes","display_name":"Gaussian processes","score":0.7699999809265137},{"id":"https://openalex.org/keywords/function-learning","display_name":"function learning","score":0.7110000252723694},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.8500000238418579},{"id":"https://openalex.org/keywords/kernel-smoothness","display_name":"kernel smoothness","score":0.6399999856948853},{"id":"https://openalex.org/keywords/likelihood-analysis","display_name":"likelihood analysis","score":0.41200000047683716},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5550000071525574},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.9909999966621399},{"id":"https://openalex.org/keywords/sample-efficiency","display_name":"sample efficiency","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.6644999980926514},{"id":"https://openalex.org/C21563000","wikidata":"https://www.wikidata.org/wiki/Q484511","display_name":"Inductive reasoning","level":2,"score":0.6218000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6159999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5824999809265137},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.474700003862381},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4052000045776367},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.11863","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.11863","pdf_url":"https://arxiv.org/pdf/2602.11863","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.2602.11863","doi":"https://doi.org/10.48550/arxiv.2602.11863","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.11863","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:2602.11863","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.11863","pdf_url":"https://arxiv.org/pdf/2602.11863","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":[{"id":"https://openalex.org/F4320317967","display_name":"International Max Planck Research School for Environmental, Cellular and Molecular Microbiology","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320327553","display_name":"International Max Planck Research School for Advanced Methods in Process and Systems Engineering","ror":"https://ror.org/04hazks31"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128809283.pdf","grobid_xml":"https://content.openalex.org/works/W7128809283.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W3208828709","https://openalex.org/W4310509152","https://openalex.org/W4323557142","https://openalex.org/W4323697341","https://openalex.org/W4327526464","https://openalex.org/W4377864715","https://openalex.org/W4385567149","https://openalex.org/W4385570910","https://openalex.org/W4387390373","https://openalex.org/W4387561528","https://openalex.org/W4388514894","https://openalex.org/W4392822465","https://openalex.org/W4394781849","https://openalex.org/W4399399219","https://openalex.org/W4401306886","https://openalex.org/W4406961529","https://openalex.org/W4409049124","https://openalex.org/W4414939355","https://openalex.org/W4417055076","https://openalex.org/W7133198810","https://openalex.org/W7133233472","https://openalex.org/W7196953391"],"related_works":["https://openalex.org/W7131744111","https://openalex.org/W7133183456","https://openalex.org/W4377864715","https://openalex.org/W4377865944","https://openalex.org/W4403924786","https://openalex.org/W4387995062","https://openalex.org/W4413855556","https://openalex.org/W3208828709","https://openalex.org/W4415795211","https://openalex.org/W4394781845"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,32,127],"(LLMs)":[3],"can":[4,150,175],"learn":[5],"from":[6,41,161],"a":[7,69,81,87,129],"few":[8],"demonstrations":[9,55,117],"provided":[10],"at":[11],"inference":[12],"time.":[13],"We":[14,27,45,119,132,166],"study":[15,121],"this":[16],"in-context":[17],"learning":[18,98,171,211],"phenomenon":[19],"through":[20],"the":[21,52,77,104,109,114,122,181,184,191],"lens":[22],"of":[23,35,54,80,116,125,183],"Gaussian":[24],"Processes":[25],"(GPs).":[26],"build":[28],"controlled":[29],"experiments":[30],"where":[31],"observe":[33],"sequences":[34],"multivariate":[36],"scalar-valued":[37],"function":[38,210],"samples":[39],"drawn":[40],"known":[42],"GP":[43,110,143,198],"priors.":[44],"evaluate":[46],"prediction":[47],"error":[48,79],"in":[49,180],"relation":[50],"to":[51,193],"number":[53,115],"and":[56,75,107,155,172,200],"compare":[57],"against":[58],"two":[59],"principled":[60],"references:":[61],"(i)":[62],"an":[63],"empirical":[64],"GP-regression":[65],"learner":[66],"that":[67,96,134,168],"gives":[68,86],"lower":[70,111],"bound":[71,112],"on":[72,158],"achievable":[73],"error,":[74],"(ii)":[76],"expected":[78],"1-nearest-neighbor":[82],"(1-NN)":[83],"rule,":[84],"which":[85,194],"data-driven":[88],"upper":[89],"bound.":[90],"Across":[91],"model":[92],"sizes,":[93],"we":[94,146],"find":[95,133,167],"LLM":[97,135],"curves":[99],"are":[100,137],"strongly":[101],"influenced":[102],"by":[103],"function-generating":[105],"kernels":[106],"approach":[108],"as":[113],"increases.":[118],"then":[120],"inductive":[123,153,178,206],"biases":[124,154,179,207],"these":[126,152],"using":[128],"likelihood-based":[130],"analysis.":[131],"predictions":[136],"most":[138],"likely":[139],"under":[140],"less":[141],"smooth":[142],"kernels.":[144,165],"Finally,":[145],"explore":[147],"whether":[148],"post-training":[149],"shift":[151,177],"improve":[156],"sample-efficiency":[157],"functions":[159],"sampled":[160],"GPs":[162],"with":[163],"smoother":[164],"both":[169],"reinforcement":[170],"supervised":[173],"fine-tuning":[174],"effectively":[176],"direction":[182],"training":[185],"data.":[186],"Together,":[187],"our":[188],"framework":[189],"quantifies":[190],"extent":[192],"LLMs":[195],"behave":[196],"like":[197],"learners":[199],"provides":[201],"tools":[202],"for":[203,208],"steering":[204],"their":[205],"continuous":[209],"tasks.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-14T00:00:00"}