{"id":"https://openalex.org/W7138230450","doi":"https://doi.org/10.1609/aaai.v40i36.40273","title":"Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective","display_name":"Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138230450","doi":"https://doi.org/10.1609/aaai.v40i36.40273"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i36.40273","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40273","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i36.40273","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129728023","display_name":"Haoyang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haoyang Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027015677","display_name":"Richong Zhang","orcid":"https://orcid.org/0000-0002-1207-0300"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richong Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006061735","display_name":"Junfan Chen","orcid":"https://orcid.org/0000-0001-6807-0089"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junfan Chen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5129728023"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44141252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"36","first_page":"30226","last_page":"30234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.24950000643730164,"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":0.24950000643730164,"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":0.20630000531673431,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0771000012755394,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6877999901771545},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6840000152587891},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5231000185012817},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4909000098705292},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.39500001072883606},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.37630000710487366},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.37610000371932983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583000063896179},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6877999901771545},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6840000152587891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6614000201225281},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5781000256538391},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.39500001072883606},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.25440001487731934},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i36.40273","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40273","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i36.40273","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40273","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7740099430084229,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,16],"models":[2,37],"(LLMs)":[3],"perform":[4],"in-context":[5],"learning":[6,92],"(ICL)":[7],"with":[8,111,131,155,162],"minimal":[9],"supervised":[10],"examples,":[11],"which":[12],"benefits":[13],"various":[14],"natural":[15],"processing":[17],"(NLP)":[18],"tasks.":[19],"One":[20],"of":[21,29,73,78,109],"the":[22,27,40,57,70,81,107,181],"critical":[23],"research":[24],"focus":[25],"is":[26,60],"selection":[28],"prompt":[30],"demonstrations.":[31,47],"Current":[32],"approaches":[33],"typically":[34],"employ":[35],"retrieval":[36],"to":[38,127,159],"select":[39],"top-K":[41],"most":[42],"semantically":[43],"similar":[44,104],"examples":[45],"as":[46,89,115],"However,":[48],"we":[49,121,139],"argue":[50],"that":[51,103],"existing":[52],"methods":[53],"are":[54],"limited":[55],"since":[56],"label":[58,83,124,129,137,149],"consistency":[59,130],"not":[61],"guaranteed":[62],"during":[63],"demonstration":[64],"selection.":[65],"Our":[66,173],"cognition":[67],"derives":[68],"from":[69,80,98],"Bayesian":[71,99],"view":[72,100],"ICL":[74,79,88],"and":[75,94,101,148,151],"our":[76],"rethinking":[77],"transductive":[82,91],"propagation":[84,125,132],"perspective.":[85],"We":[86],"treat":[87],"a":[90,123,141,176],"method":[93],"incorporate":[95],"latent":[96],"concepts":[97,108],"deduce":[102],"demonstrations":[105,161],"guide":[106],"query,":[110],"consistent":[112,163],"labels":[113],"serving":[114],"estimates.":[116],"Based":[117],"on":[118,170],"this":[119],"understanding,":[120],"establish":[122],"framework":[126],"link":[128],"error":[133],"bounds.":[134],"To":[135],"model":[136],"consistency,":[138],"propose":[140],"data":[142],"synthesis":[143],"method,":[144],"leveraging":[145],"both":[146],"semantic":[147],"information,":[150],"use":[152],"TopK":[153,168],"sampling":[154,169],"Synthetic":[156],"Data":[157],"(TopK-SD)":[158],"acquire":[160],"labels.":[164],"TopK-SD":[165],"outperforms":[166],"original":[167],"multiple":[171],"benchmarks.":[172],"work":[174],"provides":[175],"new":[177],"perspective":[178],"for":[179],"understanding":[180],"working":[182],"mechanisms":[183],"within":[184],"ICL.":[185]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}