{"id":"https://openalex.org/W7212759159","doi":"https://doi.org/10.48550/arxiv.2609.12270","title":"Recommendation Retrievers Need Verifiers: Universal Generative Reranking for Sequential Recommendations","display_name":"Recommendation Retrievers Need Verifiers: Universal Generative Reranking for Sequential Recommendations","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212759159","doi":"https://doi.org/10.48550/arxiv.2609.12270"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.12270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12270","pdf_url":"https://arxiv.org/pdf/2609.12270","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.12270","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151643428","display_name":"Benyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Benyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151661365","display_name":"Qiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126506678","display_name":"Rui Li","orcid":"https://orcid.org/0000-0001-9973-1062","observed_orcids":["https://orcid.org/0000-0001-9973-1062"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006968556","display_name":"Qunshu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qunshu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081988678","display_name":"Devansh Tandon","orcid":"https://orcid.org/0000-0002-8737-1511","observed_orcids":["https://orcid.org/0000-0002-8737-1511"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tandon, Devansh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027386790","display_name":"Neeraj Bhatia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhatia, Neeraj","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":true,"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":0.9951000213623047,"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":0.9951000213623047,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.00430000014603138,"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":0.0,"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/sequential-recommendation","display_name":"sequential recommendation","score":0.6359999775886536},{"id":"https://openalex.org/keywords/sasrec","display_name":"SASRec","score":0.6029999852180481},{"id":"https://openalex.org/keywords/music-recommendation","display_name":"music recommendation","score":0.8679999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506999969482422},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5508000254631042},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625999927520752},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40720000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3815999925136566},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2558000087738037},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.12270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12270","pdf_url":"https://arxiv.org/pdf/2609.12270","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.12270","doi":"https://doi.org/10.48550/arxiv.2609.12270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.12270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.12270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12270","pdf_url":"https://arxiv.org/pdf/2609.12270","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212759159.pdf","grobid_xml":"https://content.openalex.org/works/W7212759159.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7083167404","https://openalex.org/W7102772712","https://openalex.org/W4393159531","https://openalex.org/W7202006632","https://openalex.org/W4414035051","https://openalex.org/W7220654046","https://openalex.org/W7131394095","https://openalex.org/W4377371981","https://openalex.org/W7128553135","https://openalex.org/W7214191998"],"abstract_inverted_index":{"First-stage":[0],"recommenders":[1],"in":[2,63],"multi-stage":[3],"systems":[4],"produce":[5],"a":[6,12,98,106,110,159,214],"ranked":[7],"candidate":[8,111,139,163],"list":[9,66],"from":[10,69],"which":[11],"limited":[13],"prefix":[14,72],"is":[15,41,74,126,154],"forwarded":[16,22,50],"to":[17],"downstream":[18],"rankers.":[19],"Because":[20],"each":[21],"item":[23,58,117,167],"must":[24],"be":[25,35,60],"processed":[26],"by":[27,54,204],"more":[28],"expensive":[29],"ranking":[30],"stages,":[31],"this":[32],"shortlist":[33,89],"cannot":[34],"arbitrarily":[36],"large.":[37],"The":[38,152],"first-stage":[39],"objective":[40],"therefore":[42],"high":[43],"coverage":[44],"of":[45,121],"relevant":[46,57],"items":[47],"within":[48],"the":[49,64,70,87,94,113,116,119,146,156,166,182,198,209],"prefix,":[51],"commonly":[52],"measured":[53],"Recall@$k$.":[55],"A":[56],"may":[59],"available":[61],"deeper":[62],"retrieved":[65],"but":[67],"absent":[68],"shorter":[71],"that":[73,197],"actually":[75],"consumed.":[76],"This":[77],"paper":[78],"studies":[79],"post-hoc":[80,215],"verification":[81,212],"for":[82,102,189],"promoting":[83],"such":[84],"candidates":[85,149],"into":[86,208],"consumed":[88],"without":[90],"retraining":[91],"or":[92,138],"replacing":[93],"retriever.":[95],"We":[96],"introduce":[97],"lightweight":[99],"generative":[100],"verifier":[101,114,184],"retrieval":[103],"models.":[104],"Given":[105],"retriever":[107,157],"state":[108,161],"and":[109,143,162,165,178,193],"item,":[112],"scores":[115,144],"through":[118],"likelihood":[120],"its":[122],"identifier":[123],"tokens.":[124],"It":[125],"trained":[127],"post":[128],"hoc":[129],"with":[130],"next-token":[131],"cross":[132],"entropy,":[133],"requires":[134],"no":[135],"sampled":[136],"negatives":[137],"pool":[140],"during":[141],"training,":[142],"only":[145],"retriever's":[147],"top-$K$":[148],"at":[150],"inference.":[151],"interface":[153],"minimal:":[155],"supplies":[158],"query":[160],"items,":[164],"representation":[168],"can":[169],"use":[170],"any":[171],"fixed":[172],"tokenization.":[173],"Across":[174],"Amazon":[175],"product":[176],"recommendation":[177],"YaMBDa":[179],"music":[180],"recommendation,":[181],"same":[183],"training":[185],"recipe":[186],"improves":[187],"Recall@10":[188],"SASRec,":[190],"GRU4Rec,":[191],"NextItNet,":[192],"MiniOneRec.":[194],"Ablations":[195],"show":[196],"improvements":[199],"are":[200],"not":[201],"explained":[202],"solely":[203],"injecting":[205],"item-content":[206],"features":[207],"retriever,":[210],"supporting":[211],"as":[213],"output-side":[216],"adaptation":[217],"mechanism.":[218]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-15T00:00:00"}