{"id":"https://openalex.org/W6948294992","doi":"https://doi.org/10.48550/arxiv.2503.06358","title":"Language Model Personalization via Reward Factorization","display_name":"Language Model Personalization via Reward Factorization","publication_year":2025,"publication_date":"2025-03-08","ids":{"openalex":"https://openalex.org/W6948294992","doi":"https://doi.org/10.48550/arxiv.2503.06358"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.06358","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06358","pdf_url":"https://arxiv.org/pdf/2503.06358","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.06358","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052622748","display_name":"Idan Shenfeld","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shenfeld, Idan","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061079282","display_name":"Felix Faltings","orcid":"https://orcid.org/0009-0002-8424-7467","observed_orcids":["https://orcid.org/0009-0002-8424-7467"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faltings, Felix","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111774389","display_name":"Pulkit Agrawal","orcid":"https://orcid.org/0000-0001-8463-9917","observed_orcids":["https://orcid.org/0000-0001-8463-9917","https://orcid.org/0000-0002-9569-6690"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agrawal, Pulkit","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006761546","display_name":"Aldo Pacchiano","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pacchiano, Aldo","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":33,"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":true,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.22849999368190765,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.22849999368190765,"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":0.16539999842643738,"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":0.164900004863739,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7009999752044678},{"id":"https://openalex.org/keywords/user-personalization","display_name":"user personalization","score":0.8450000286102295},{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.9380000233650208}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8600999712944031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091999888420105},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5522000193595886},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.49070000648498535},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.06358","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06358","pdf_url":"https://arxiv.org/pdf/2503.06358","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.06358","doi":"https://doi.org/10.48550/arxiv.2503.06358","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.06358","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:2503.06358","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06358","pdf_url":"https://arxiv.org/pdf/2503.06358","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1425446948","display_name":null,"funder_award_id":"W911NF-21-1-0328","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G1495680632","display_name":null,"funder_award_id":"W911NF-21-1-0328","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G2952323941","display_name":null,"funder_award_id":"W911NF-23-1-0277","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G3938712152","display_name":null,"funder_award_id":"N00014-22-1-2740","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4005539596","display_name":null,"funder_award_id":"W911NF-23-1-0277","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8857636796","display_name":null,"funder_award_id":"N00014-22-1-2740","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6948294992.pdf","grobid_xml":"https://content.openalex.org/works/W6948294992.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2973379954","https://openalex.org/W4223908421","https://openalex.org/W4311991106","https://openalex.org/W4385436553","https://openalex.org/W4387800281","https://openalex.org/W4387995048","https://openalex.org/W4388261654","https://openalex.org/W4390833718","https://openalex.org/W4391591625","https://openalex.org/W4391670400","https://openalex.org/W4391871179","https://openalex.org/W4391901224","https://openalex.org/W4392089896","https://openalex.org/W4396907085","https://openalex.org/W4399657817","https://openalex.org/W4400222256","https://openalex.org/W4402670165","https://openalex.org/W4402853841","https://openalex.org/W4403322392","https://openalex.org/W4403702639","https://openalex.org/W4404344563","https://openalex.org/W4404781419","https://openalex.org/W4404783337","https://openalex.org/W4404792842","https://openalex.org/W4405655184","https://openalex.org/W4414544662","https://openalex.org/W4415795999","https://openalex.org/W4415797665","https://openalex.org/W4416017534"],"related_works":["https://openalex.org/W4391709257","https://openalex.org/W6891914921","https://openalex.org/W4415238136","https://openalex.org/W4400434452","https://openalex.org/W4416054679","https://openalex.org/W4415330372","https://openalex.org/W4416036595","https://openalex.org/W7167932541","https://openalex.org/W7164042369","https://openalex.org/W4387800281"],"abstract_inverted_index":{"Modern":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"are":[5],"optimized":[6],"for":[7,30],"human-aligned":[8],"responses":[9],"using":[10],"Reinforcement":[11],"Learning":[12],"from":[13],"Human":[14],"Feedback":[15],"(RLHF).":[16],"However,":[17],"existing":[18],"RLHF":[19,46],"approaches":[20],"assume":[21],"a":[22,42,60,66,76,124],"universal":[23],"preference":[24],"model":[25,68],"and":[26,94,108],"fail":[27],"to":[28,47],"account":[29],"individual":[31],"user":[32,49,56,86],"preferences,":[33],"limiting":[34],"their":[35],"effectiveness":[36],"in":[37,59],"personalized":[38],"applications.":[39],"We":[40,99],"introduce":[41],"framework":[43],"that":[44,55],"extends":[45],"enable":[48],"personalization":[50,113],"by":[51,115],"leveraging":[52],"the":[53],"assumption":[54],"preferences":[57],"lie":[58],"low-dimensional":[61],"space.":[62],"Instead":[63],"of":[64,79],"training":[65],"separate":[67],"per":[69],"user,":[70],"we":[71],"represent":[72],"user-specific":[73,92],"rewards":[74,93],"as":[75],"linear":[77],"combination":[78],"base":[80],"reward":[81],"functions.":[82],"Using":[83],"only":[84],"~10":[85],"responses,":[87],"our":[88,101,116,121],"method":[89,122],"can":[90],"infer":[91],"align":[95],"LLM":[96],"outputs":[97],"accordingly.":[98],"validate":[100],"approach":[102],"through":[103],"experiments":[104],"with":[105],"both":[106],"synthetic":[107],"real":[109],"users,":[110],"demonstrating":[111],"significant":[112],"achieved":[114],"method.":[117],"In":[118],"human":[119],"evaluations,":[120],"achieves":[123],"67%":[125],"win":[126],"rate":[127],"over":[128],"default":[129],"GPT-4o":[130],"responses.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":28},{"year":2025,"cited_by_count":5}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}