{"id":"https://openalex.org/W7164863299","doi":"https://doi.org/10.48550/arxiv.2606.14142","title":"Implicit Reasoning for Large Language Model-based Generative Recommendation","display_name":"Implicit Reasoning for Large Language Model-based Generative Recommendation","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164863299","doi":"https://doi.org/10.48550/arxiv.2606.14142"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.14142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14142","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.14142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121999607","display_name":"Y He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yinhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138679859","display_name":"Liam Collins","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Collins, Liam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121099393","display_name":"Bhuvesh Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Bhuvesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138630022","display_name":"Jundong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jundong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138655005","display_name":"Neil Shah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Neil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122229439","display_name":"Donald Loveland","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loveland, Donald","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/T10028","display_name":"Topic Modeling","score":0.322299987077713,"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/T10028","display_name":"Topic Modeling","score":0.322299987077713,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.149399995803833,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.11429999768733978,"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/security-token","display_name":"Security token","score":0.578499972820282},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5530999898910522},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5135999917984009},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.4544000029563904},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.390500009059906},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3776000142097473},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.3752000033855438},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.365200012922287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470999956130981},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.390500009059906},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3257000148296356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3172000050544739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C2780565519","wikidata":"https://www.wikidata.org/wiki/Q1208937","display_name":"Multitude","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.14142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14142","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.14142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14142","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,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4146304726600647}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4,51],"increasingly":[5],"adopted":[6],"as":[7,195],"backbones":[8],"for":[9,24,95,138],"Generative":[10],"Recommendation":[11],"(GR),":[12],"promising":[13],"access":[14],"to":[15,115,154,168,177,189,199],"pretrained":[16],"world":[17],"knowledge.":[18],"Yet":[19],"reliably":[20],"invoking":[21],"this":[22,61,86],"knowledge":[23],"GR":[25,35],"remains":[26],"poorly":[27],"understood.":[28],"A":[29],"key":[30,100],"obstacle":[31],"is":[32,83,141],"that":[33,66],"LLM-based":[34,96,208],"typically":[36],"represents":[37],"items":[38],"with":[39,62],"Semantic":[40],"IDs":[41],"(SIDs),":[42],"disrupting":[43],"LLMs'":[44],"natural-language":[45,109],"reasoning":[46,92,123,135,146,150],"interface":[47],"because":[48],"these":[49,127],"tokens":[50],"unseen":[52],"by":[53,166,175,187],"the":[54],"LLM":[55],"during":[56],"pretraining.":[57],"Existing":[58],"approaches":[59],"address":[60],"expensive":[63],"multi-stage":[64],"pipelines":[65,94],"ground":[67],"SIDs":[68],"and":[69,79,108,113,149,181,206],"elicit":[70],"explicit":[71,91,122,163,200],"rationales,":[72],"but":[73],"offer":[74],"limited":[75],"insight":[76],"into":[77],"when":[78],"why":[80],"each":[81],"stage":[82],"necessary.":[84],"In":[85],"work,":[87],"we":[88,129],"systematically":[89],"decompose":[90],"training":[93,173],"GR,":[97],"revealing":[98],"three":[99],"limitations:":[101],"weakened":[102],"world-knowledge":[103],"verbalization,":[104],"misalignment":[105],"between":[106],"SID":[107],"token":[110],"embedding":[111],"spaces,":[112],"sensitivity":[114],"rationale":[116,201],"quality,":[117],"all":[118],"of":[119,157],"which":[120],"hurt":[121],"performance.":[124],"To":[125],"circumvent":[126],"issues,":[128],"propose":[130],"PauseRec,":[131],"a":[132,155,196],"lightweight":[133,197],"implicit":[134],"paradigm":[136],"tailored":[137],"GR.":[139,209],"PauseRec":[140,194],"exceptionally":[142],"practical,":[143],"avoiding":[144],"costly":[145],"trace":[147],"acquisition":[148],"alignment":[151],"training,":[152],"leading":[153],"multitude":[156],"benefits:":[158],"(1)":[159],"it":[160,171,183],"outperforms":[161],"standard":[162],"CoT":[164],"methods":[165],"up":[167,176,185,188],"6.22%,":[169],"(2)":[170],"reduces":[172],"cost":[174],"65%":[178],"GPU":[179],"hours,":[180],"(3)":[182],"speeds":[184],"inference":[186],"71.3%.":[190],"These":[191],"results":[192],"position":[193],"alternative":[198],"generation,":[202],"enabling":[203],"more":[204],"effective":[205],"efficient":[207]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-16T00:00:00"}