{"id":"https://openalex.org/W7154446566","doi":"https://doi.org/10.48550/arxiv.2604.12096","title":"LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks","display_name":"LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154446566","doi":"https://doi.org/10.48550/arxiv.2604.12096"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.12096","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12096","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2604.12096","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013776504","display_name":"Luyi Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Luyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133683368","display_name":"Wanjia Sherry Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wanjia Sherry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133635025","display_name":"Zezhong Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Zezhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133678465","display_name":"Shubham Thakur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thakur, Shubham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133681064","display_name":"Kai Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110429504","display_name":"K. C. Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Kehui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112724938","display_name":"Ayush Agarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Ayush","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109292369","display_name":"Rahul Iyer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iyer, Rahul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001968450","display_name":"Jason Cho","orcid":"https://orcid.org/0000-0002-8106-2961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cho, Jason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133657827","display_name":"Jianpeng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jianpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133672576","display_name":"Evren Korpeoglu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korpeoglu, Evren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133662682","display_name":"Sushant Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Sushant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133657088","display_name":"Kannan Achan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Achan, Kannan","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/T10609","display_name":"Digital Marketing and Social Media","score":0.21389999985694885,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10609","display_name":"Digital Marketing and Social Media","score":0.21389999985694885,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.17139999568462372,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.15610000491142273,"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/normalization","display_name":"Normalization (sociology)","score":0.5913000106811523},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5073000192642212},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48669999837875366},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.45260000228881836},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41670000553131104},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.39239999651908875},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.39010000228881836},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.375},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004999756813049},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927999973297119},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41670000553131104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.375},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C115174607","wikidata":"https://www.wikidata.org/wiki/Q1100934","display_name":"Click-through rate","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.12096","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12096","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2604.12096","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.12096","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"On":[0],"online":[1,140],"advertising":[2],"platforms,":[3],"newly":[4],"introduced":[5],"promotional":[6],"ads":[7],"face":[8],"the":[9,41,44,90,117,146,151,154,162],"cold-start":[10,132,163],"problem,":[11],"as":[12,36],"they":[13],"lack":[14],"sufficient":[15],"user":[16],"feedback":[17],"for":[18,70],"model":[19,68],"training.":[20],"In":[21],"this":[22],"work,":[23],"we":[24,109],"propose":[25],"LLM-HYPER,":[26,158],"a":[27,50,71],"novel":[28],"framework":[29],"that":[30,115,128],"treats":[31],"large":[32],"language":[33],"models":[34],"(LLMs)":[35],"hypernetworks":[37],"to":[38,65,93],"directly":[39],"generate":[40],"parameters":[42],"of":[43,145,157],"click-through":[45],"rate":[46],"(CTR)":[47],"estimator":[48],"in":[49,134,150,174],"training-free":[51],"manner.":[52],"LLM-HYPER":[53,129,169],"uses":[54],"few-shot":[55],"Chain-of-Thought":[56],"prompting":[57],"over":[58],"multimodal":[59],"ad":[60],"content":[61,101],"(text":[62],"and":[63,84,100,107,112,165],"images)":[64],"infer":[66],"feature-wise":[67],"weights":[69,119],"linear":[72],"CTR":[73,122],"predictor.":[74],"By":[75],"retrieving":[76],"semantically":[77],"similar":[78],"past":[79],"campaigns":[80],"via":[81],"CLIP":[82],"embeddings":[83],"formatting":[85],"them":[86],"into":[87],"prompt-based":[88],"demonstrations,":[89],"LLM":[91],"learns":[92],"reason":[94],"about":[95],"customer":[96],"intent,":[97],"feature":[98],"influence,":[99],"relevance.":[102],"To":[103],"ensure":[104],"numerical":[105],"stability":[106],"serviceability,":[108],"introduce":[110],"normalization":[111],"calibration":[113],"techniques":[114],"align":[116],"generated":[118],"with":[120],"production-ready":[121],"distributions.":[123],"Extensive":[124],"offline":[125],"experiments":[126],"show":[127],"significantly":[130],"outperforms":[131],"baselines":[133],"NDCG$@10$":[135],"by":[136],"55.9\\%.":[137],"Our":[138],"real-world":[139],"A/B":[141],"test":[142],"on":[143],"one":[144],"top":[147],"e-commerce":[148],"platforms":[149],"U.S.":[152],"demonstrates":[153],"strong":[155],"performance":[156],"which":[159],"drastically":[160],"reduces":[161],"period":[164],"achieves":[166],"competitive":[167],"performance.":[168],"has":[170],"been":[171],"successfully":[172],"deployed":[173],"production.":[175]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-16T00:00:00"}