{"id":"https://openalex.org/W7154730653","doi":"https://doi.org/10.48550/arxiv.2604.14878","title":"GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation","display_name":"GenRec: A Preference-Oriented Generative Framework for Large-Scale Recommendation","publication_year":2026,"publication_date":"2026-04-16","ids":{"openalex":"https://openalex.org/W7154730653","doi":"https://doi.org/10.48550/arxiv.2604.14878"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.14878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14878","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.14878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133837855","display_name":"Yanyan Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zou, Yanyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133864567","display_name":"Junbo Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Junbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133844884","display_name":"Lunsong Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Lunsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133900684","display_name":"Yu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122955745","display_name":"Kewei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Kewei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133850680","display_name":"Jiabao Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jiabao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068422435","display_name":"Binglei Zhao","orcid":"https://orcid.org/0000-0002-5390-1983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Binglei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074108489","display_name":"Xuanhua Yang","orcid":"https://orcid.org/0009-0005-6644-627X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xuanhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133838562","display_name":"Sulong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Sulong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133872823","display_name":"Shengjie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5133837855"],"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9437000155448914,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9437000155448914,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.008500000461935997,"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":0.006099999882280827,"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/generative-grammar","display_name":"Generative grammar","score":0.5853000283241272},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5741999745368958},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.550000011920929},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5353999733924866},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44679999351501465},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.4458000063896179},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4424999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5853000283241272},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44679999351501465},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4074999988079071},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2720000147819519}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.14878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14878","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.14878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.14878","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Generative":[0],"Retrieval":[1],"(GR)":[2],"offers":[3],"a":[4,25,74,88,164,185,190],"promising":[5],"paradigm":[6],"for":[7,177],"recommendation":[8],"through":[9],"next-token":[10],"prediction":[11],"(NTP).":[12],"However,":[13],"scaling":[14],"it":[15],"to":[16,37,193],"large-scale":[17],"industrial":[18],"systems":[19],"introduces":[20],"three":[21],"challenges:":[22],"(i)":[23],"within":[24,87],"single":[26,89],"request,":[27],"the":[28,38,43,63,80,119,126,139,218],"identical":[29],"model":[30,188],"inputs":[31],"may":[32],"produce":[33],"inconsistent":[34],"outputs":[35,157],"due":[36],"pagination":[39],"request":[40],"mechanism;":[41],"(ii)":[42],"prohibitive":[44],"cost":[45],"of":[46,122],"encoding":[47],"long":[48],"user":[49,68,159],"behavior":[50],"sequences":[51],"with":[52,66,150,158,174,189],"multi-token":[53,135],"item":[54,111],"representations":[55],"based":[56],"on":[57,79],"semantic":[58],"IDs,":[59],"and":[60,117,180,212],"(iii)":[61],"aligning":[62],"generative":[64,76],"policy":[65],"nuanced":[67],"preference":[69],"signals.":[70],"We":[71],"present":[72],"GenRec,":[73],"preference-oriented":[75],"framework":[77],"deployed":[78],"JD":[81],"App":[82],"that":[83,168],"addresses":[84],"above":[85],"challenges":[86],"decoder-only":[90],"architecture.":[91],"For":[92],"training":[93,178],"objective,":[94],"we":[95,161],"propose":[96],"Page-wise":[97],"NTP":[98],"task,":[99],"which":[100],"supervises":[101],"over":[102,217],"an":[103,129],"entire":[104],"interaction":[105],"page":[106],"rather":[107],"than":[108],"each":[109],"interacted":[110],"individually,":[112],"providing":[113],"denser":[114],"gradient":[115],"signal":[116],"resolving":[118],"one-to-many":[120],"ambiguity":[121],"point-wise":[123],"training.":[124],"On":[125],"prefilling":[127],"side,":[128],"asymmetric":[130],"linear":[131],"Token":[132],"Merger":[133],"compresses":[134],"Semantic":[136],"IDs":[137],"in":[138,209,214],"prompt":[140],"while":[141],"preserving":[142],"full-resolution":[143],"decoding,":[144],"reducing":[145],"input":[146],"length":[147],"by":[148],"~2X":[149],"negligible":[151],"accuracy":[152],"loss.":[153],"To":[154],"further":[155],"align":[156],"satisfaction,":[160],"introduce":[162],"GRPO-SR,":[163],"reinforcement":[165],"learning":[166],"method":[167],"pairs":[169],"Group":[170],"Relative":[171],"Policy":[172],"Optimization":[173],"NLL":[175],"regularization":[176],"stability,":[179],"employs":[181],"Hybrid":[182],"Rewards":[183],"combining":[184],"dense":[186],"reward":[187,195],"relevance":[191],"gate":[192],"mitigate":[194],"hacking.":[196],"In":[197],"month-long":[198],"online":[199],"A/B":[200],"tests":[201],"serving":[202],"production":[203],"traffic,":[204],"GenRec":[205],"achieves":[206],"9.5%":[207],"improvement":[208],"click":[210],"count":[211,216],"8.7%":[213],"transaction":[215],"existing":[219],"pipeline.":[220]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-18T00:00:00"}