{"id":"https://openalex.org/W7137934711","doi":"https://doi.org/10.1609/aaai.v40i18.38590","title":"Think Wise, Collaborate Effectively: A Rationale-Aware LLM-Based Recommender with Reinforcement Learning from Collaborative Signals","display_name":"Think Wise, Collaborate Effectively: A Rationale-Aware LLM-Based Recommender with Reinforcement Learning from Collaborative Signals","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137934711","doi":"https://doi.org/10.1609/aaai.v40i18.38590"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i18.38590","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38590","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i18.38590","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129743730","display_name":"Chung Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung Park","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686693","display_name":"Taesan Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taesan Kim","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026828476","display_name":"Hyeongjun Yun","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210149944","display_name":"Korea Telecom (South Korea)","ror":null,"country_code":"KR","type":null,"lineage":["https://openalex.org/I4210149944"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeongjun Yun","raw_affiliation_strings":["SK Telecom\nKorea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom\nKorea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210149944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103914167","display_name":"D. J. Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongjoon Hong","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129748027","display_name":"Junui Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junui Hong","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026375238","display_name":"Kijung Park","orcid":"https://orcid.org/0000-0001-9672-8802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kijung Park","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102840343","display_name":"Mincheol Cho","orcid":"https://orcid.org/0009-0006-6219-245X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MinCheol Cho","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716389","display_name":"Min Sung Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Sung Choi","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125758474","display_name":"Jihwan Seok","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihwan Seok","raw_affiliation_strings":["SK Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SK Telecom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129664076","display_name":"Jaegul Choo","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaegul Choo","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18867925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"18","first_page":"15609","last_page":"15616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.4058000147342682,"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":0.4058000147342682,"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":0.2538999915122986,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0560000017285347,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/recommender-system","display_name":"Recommender system","score":0.7164000272750854},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.6759999990463257},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6004999876022339},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5403000116348267},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.38339999318122864},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3598000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003000020980835},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7164000272750854},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.6759999990463257},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5067999958992004},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C554579003","wikidata":"https://www.wikidata.org/wiki/Q474157","display_name":"Collaborative software","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i18.38590","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38590","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38590","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i18.38590","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i18.38590","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-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":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"recently":[5],"emerged":[6],"as":[7,27],"powerful":[8],"reasoning":[9],"engines":[10],"in":[11,117,198,228],"recommender":[12,70],"systems,":[13],"generating":[14],"natural-language":[15],"explanations":[16],"that":[17,71,101,157,195],"foster":[18],"user":[19,160],"engagement.":[20],"However,":[21],"their":[22],"recommendation":[23,173,231],"performance":[24,44,174,232],"remains":[25],"limited,":[26],"they":[28],"lack":[29],"exposure":[30],"to":[31,97,147,154,169,200],"collaborative":[32,38,73],"user-item":[33,74,177],"interaction":[34,109,178],"patterns.":[35],"In":[36,76,123,236],"contrast,":[37],"filtering":[39],"(CF)":[40],"models":[41,224],"achieve":[42,186],"strong":[43],"by":[45,85,175],"learning":[46,88,193],"from":[47,181,212],"these":[48],"behavioral":[49],"patterns":[50,179],"at":[51],"scale.":[52],"To":[53,185],"unify":[54],"the":[55,77,103,107,112,124,133,149,152,171,182,202,207,210,213],"strengths":[56],"of":[57,230],"both":[58,141,201,220],"paradigms,":[59],"we":[60,80,127,167,188],"propose":[61,189],"TWiCE-Rec":[62],"(Think":[63],"Wise,":[64],"Collaborate":[65],"Effectively),":[66],"a":[67,82,118,190],"rationale-aware":[68],"LLM-based":[69],"incorporates":[72],"interactions.":[75],"first":[78],"stage,":[79,126],"construct":[81],"rationale":[83,234],"dataset":[84],"applying":[86],"in-context":[87],"with":[89,151,163,206],"self-annotated":[90],"curation.":[91],"A":[92],"state-of-the-art":[93],"LLM":[94,150],"is":[95],"guided":[96],"generate":[98,155],"persuasive":[99],"rationales":[100,156],"explain":[102],"causal":[104],"relationship":[105],"between":[106],"user\u2019s":[108],"sequence":[110],"and":[111,140,143,209,222,233],"ground-truth":[113,208],"next":[114],"item,":[115],"resulting":[116],"curated":[119],"post-hoc":[120],"training":[121,135],"dataset.":[122],"second":[125],"perform":[128],"multi-task":[129],"instruction-tuned":[130],"adaptation\u2014based":[131],"on":[132,225],"rationale-augmented":[134],"dataset\u2014comprising":[136],"item":[137,164],"description":[138],"generation":[139],"non-reasoning":[142],"reasoning-based":[144],"sequential":[145],"recommendation,":[146],"equip":[148],"ability":[153],"reflect":[158],"how":[159],"preferences":[161],"align":[162],"characteristics.":[165],"Finally,":[166],"aim":[168],"enhance":[170],"LLM\u2019s":[172,203],"incorporating":[176],"derived":[180],"CF-Rec":[183,215],"model.":[184,216],"this,":[187],"confidence-weighted":[191],"reinforcement":[192],"strategy":[194],"adjusts":[196],"rewards":[197],"proportion":[199],"prediction":[204],"alignment":[205],"confidence":[211],"pretrained":[214],"Our":[217],"method":[218],"outperforms":[219],"CF-":[221],"LLM-Rec":[223],"Amazon":[226],"datasets":[227],"terms":[229],"quality.":[235],"an":[237],"online":[238],"A/B":[239],"test,":[240],"it":[241],"achieved":[242],"about":[243],"8%":[244],"higher":[245],"click-through":[246],"rate":[247],"than":[248],"existing":[249],"models,":[250],"demonstrating":[251],"practical":[252],"value.":[253]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}