{"id":"https://openalex.org/W7161763310","doi":"https://doi.org/10.48550/arxiv.2605.18771","title":"LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation","display_name":"LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation","publication_year":2026,"publication_date":"2026-04-16","ids":{"openalex":"https://openalex.org/W7161763310","doi":"https://doi.org/10.48550/arxiv.2605.18771"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.18771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18771","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.2605.18771","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130577360","display_name":"Lingyu Mu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu, Lingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136606546","display_name":"Hao Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136577615","display_name":"Haibo Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Haibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136555489","display_name":"Kaican Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Kaican","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136570515","display_name":"Zhitong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136530336","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0009-3822-509X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136532990","display_name":"Xiaoyi Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Xiaoyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014956766","display_name":"Zhengxiao Liu","orcid":"https://orcid.org/0009-0009-1588-1115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhengxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136560563","display_name":"Zheng Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136523928","display_name":"Jinxin Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Jinxin","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/T10203","display_name":"Recommender Systems and Techniques","score":0.45989999175071716,"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":0.45989999175071716,"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/T10028","display_name":"Topic Modeling","score":0.09809999912977219,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0746999979019165,"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":0.47380000352859497},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.40869998931884766},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.37439998984336853},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.32019999623298645},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.3156000077724457},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.28769999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703999876976013},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47279998660087585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43950000405311584},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.18771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18771","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.2605.18771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18771","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2],"large":[3],"language":[4],"model":[5],"(LLM)":[6],"based":[7],"generative":[8,89],"recommendation":[9],"(GR)":[10],"shows":[11],"that":[12,76,152,170],"leveraging":[13],"LLM":[14,109,146],"world":[15,84,110],"knowledge":[16,33,57,85,97,114],"can":[17],"substantially":[18],"improve":[19],"performance.":[20],"However,":[21],"existing":[22],"methods":[23],"rely":[24],"on":[25,161,186],"fixed,":[26],"manually":[27],"designed":[28],"instructions":[29,46,105],"to":[30,80,106,133,178],"generate":[31],"semantic":[32],"and":[34,64,99,112,148,165,180,194],"directly":[35],"incorporate":[36,135],"it":[37],"into":[38,88],"GR,":[39],"which":[40,125],"has":[41],"two":[42,95,141],"limitations.":[43],"First,":[44],"fixed":[45],"cannot":[47],"capture":[48],"the":[49],"multidimensional":[50],"heterogeneity":[51],"of":[52],"user":[53],"interests.":[54],"Second,":[55],"uncontrollable":[56],"fusion":[58,115],"may":[59],"conflict":[60],"with":[61,120,156],"behavioral":[62],"signals":[63],"harm":[65],"recommendations.":[66],"To":[67],"address":[68],"these":[69],"limitations,":[70],"we":[71],"propose":[72],"LWGR,":[73],"a":[74,129,149,182,187],"framework":[75],"leverages":[77],"Lagrangian":[78,130],"constraints":[79],"transfer":[81],"users'":[82],"personalized":[83,103],"from":[86],"LLMs":[87],"recommendation.":[90],"LWGR":[91,171],"enhances":[92],"GR":[93],"along":[94],"axes:":[96],"extraction":[98],"fusion.":[100],"It":[101],"builds":[102],"soft":[104],"extract":[107],"behavior-relevant":[108],"knowledge,":[111],"formulates":[113],"as":[116],"an":[117],"optimization":[118],"problem":[119],"explicitly":[121],"bounded":[122],"performance":[123],"degradation,":[124],"is":[126],"solved":[127],"by":[128,176],"primal-dual":[131],"method":[132],"selectively":[134],"beneficial":[136],"knowledge.":[137],"We":[138],"further":[139],"design":[140],"training":[142],"strategies":[143],"for":[144],"different":[145],"scales":[147],"deployment":[150],"scheme":[151],"combines":[153],"nearline":[154],"precomputation":[155],"lightweight":[157],"online":[158],"serving.":[159],"Experiments":[160],"multiple":[162],"public":[163],"datasets":[164],"one":[166],"industrial":[167],"dataset":[168],"show":[169],"outperforms":[172],"eight":[173],"state-of-the-art":[174],"baselines":[175],"up":[177],"11.23%":[179],"brings":[181],"1.35%":[183],"revenue":[184],"lift":[185],"large-scale":[188],"advertising":[189],"platform,":[190],"demonstrating":[191],"its":[192],"effectiveness":[193],"practicality.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}