{"id":"https://openalex.org/W7139054195","doi":"https://doi.org/10.1609/aaai.v40i44.41089","title":"Selective Weak-to-Strong Generalization","display_name":"Selective Weak-to-Strong Generalization","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7139054195","doi":"https://doi.org/10.1609/aaai.v40i44.41089"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i44.41089","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i44.41089","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41089/45050","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41089/45050","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100618393","display_name":"Hao Lang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Lang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129804383","display_name":"Fei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130019780","display_name":"Yongbin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongbin Li","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"44","first_page":"37556","last_page":"37564"},"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":0.39910000562667847,"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":0.39910000562667847,"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":0.1881999969482422,"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":0.0786999985575676,"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/generalization","display_name":"Generalization","score":0.6624000072479248},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5649999976158142},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5590000152587891},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.5382000207901001},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43950000405311584},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4189999997615814}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6624000072479248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.586899995803833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796999931335449},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5649999976158142},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4189999997615814},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.3116999864578247},{"id":"https://openalex.org/C65180967","wikidata":"https://www.wikidata.org/wiki/Q130901","display_name":"Binary relation","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2775000035762787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i44.41089","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i44.41089","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41089/45050","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.v40i44.41089","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i44.41089","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41089/45050","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7139054195.pdf","grobid_xml":"https://content.openalex.org/works/W7139054195.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Future":[0],"superhuman":[1,18],"models":[2],"will":[3,11],"surpass":[4],"the":[5,22,55],"ability":[6],"of":[7,24,58,71],"humans":[8,10],"and":[9,109,148],"only":[12],"be":[13],"able":[14],"to":[15,76,87,100],"\\textit{weakly}":[16],"supervise":[17],"models.":[19,77],"To":[20],"alleviate":[21],"issue":[23],"lacking":[25],"high-quality":[26],"data":[27],"for":[28,114],"model":[29,41,106],"alignment,":[30],"some":[31],"works":[32],"on":[33,128],"weak-to-strong":[34],"generalization":[35],"(W2SG)":[36],"finetune":[37],"a":[38,43,69,83,96,104,122],"strong":[39,105],"pretrained":[40],"with":[42,68,121],"weak":[44,52,59,72,90,119],"supervisor":[45],"so":[46],"that":[47,103,132,142],"it":[48],"can":[49,107,144,154],"generalize":[50,145],"beyond":[51],"supervision.":[53],"However,":[54],"invariable":[56],"use":[57,110],"supervision":[60,91],"in":[61,66],"existing":[62],"methods":[63],"exposes":[64],"issues":[65],"robustness,":[67],"proportion":[70],"labels":[73,113,120],"proving":[74],"harmful":[75],"In":[78],"this":[79],"paper,":[80],"we":[81],"propose":[82],"selective":[84,152],"W2SG":[85,153],"framework":[86],"avoid":[88],"using":[89],"when":[92],"unnecessary.":[93],"We":[94,116],"train":[95],"binary":[97],"classifier":[98],"P(IK)":[99,143],"identify":[101],"questions":[102],"answer":[108],"its":[111],"self-generated":[112],"alignment.":[115],"further":[117],"refine":[118],"graph":[123],"smoothing":[124],"method.":[125],"Extensive":[126],"experiments":[127],"three":[129],"benchmarks":[130],"show":[131,141],"our":[133],"method":[134],"consistently":[135],"outperforms":[136],"competitive":[137],"baselines.":[138],"Further":[139],"analyses":[140],"across":[146],"tasks":[147],"difficulties,":[149],"which":[150],"indicates":[151],"help":[155],"superalignment.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-20T00:00:00"}