{"id":"https://openalex.org/W7134955250","doi":"https://doi.org/10.48550/arxiv.2603.09250","title":"Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval","display_name":"Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134955250","doi":"https://doi.org/10.48550/arxiv.2603.09250"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.09250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09250","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.2603.09250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128705012","display_name":"Yingyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128786585","display_name":"Junyi Jessy Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Junyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128749974","display_name":"Wenlin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128768372","display_name":"Penyue Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Penyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071228543","display_name":"Xianneng Li","orcid":"https://orcid.org/0000-0003-4130-6930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xianneng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128764347","display_name":"Yichao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081695896","display_name":"Derong Xu","orcid":"https://orcid.org/0000-0002-3971-9907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Derong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128730619","display_name":"Yi Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128798075","display_name":"Huifeng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Huifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128713691","display_name":"Yong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128770691","display_name":"Xiangyu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xiangyu","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":0.7139000296592712,"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":0.7139000296592712,"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":0.05290000140666962,"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"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.03590000048279762,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.7050999999046326},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.5177000164985657},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4523000121116638},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4519999921321869},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42879998683929443},{"id":"https://openalex.org/keywords/adaptive-memory","display_name":"Adaptive memory","score":0.41819998621940613},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4058000147342682},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.40230000019073486}],"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/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.7050999999046326},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.5177000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756999909877777},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4519999921321869},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C30390489","wikidata":"https://www.wikidata.org/wiki/Q4680748","display_name":"Adaptive memory","level":3,"score":0.41819998621940613},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.09250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09250","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.2603.09250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09250","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6317832469940186}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Personalized":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"rely":[5],"on":[6],"memory":[7,28,56,122],"retrieval":[8,39,88,97,143,209],"to":[9,85,91,100,138,167],"incorporate":[10],"user-specific":[11],"histories,":[12],"preferences,":[13],"and":[14,35,68,89,133,161,190,199,210,216],"contexts.":[15],"Existing":[16],"approaches":[17],"either":[18,101],"overload":[19],"the":[20,25,30,83,95,105,126,130,139,149,153,156,165,185,225],"LLM":[21],"by":[22],"feeding":[23],"all":[24],"user's":[26],"past":[27],"into":[29,40,184],"prompt,":[31],"which":[32,45],"is":[33],"costly":[34],"unscalable,":[36],"or":[37,104],"simplify":[38],"a":[41,59,118],"one-shot":[42,208],"similarity":[43],"search,":[44],"captures":[46],"only":[47],"surface":[48],"matches.":[49],"Cognitive":[50],"science,":[51],"however,":[52],"shows":[53],"that":[54,203],"human":[55],"operates":[57],"through":[58,129],"dual":[60,96],"process:":[61],"Familiarity,":[62],"offering":[63],"fast":[64],"but":[65],"coarse":[66],"recognition,":[67],"Recollection,":[69],"enabling":[70,191],"deliberate,":[71],"chain-like":[72],"reconstruction":[73],"for":[74],"deeply":[75],"recovering":[76],"episodic":[77],"content.":[78],"Current":[79],"systems":[80],"lack":[81],"both":[82,207],"ability":[84],"perform":[86],"recollection":[87],"mechanisms":[90],"adaptively":[92],"switch":[93],"between":[94],"paths,":[98],"leading":[99],"insufficient":[102],"recall":[103],"inclusion":[106],"of":[107],"noise.":[108],"To":[109],"address":[110],"this,":[111],"we":[112],"propose":[113],"RF-Mem":[114,124,204],"(Recollection-Familiarity":[115],"Memory":[116],"Retrieval),":[117],"familiarity":[119,127,136,147],"uncertainty-guided":[120],"dual-path":[121],"retriever.":[123],"measures":[125],"signal":[128],"mean":[131],"score":[132],"entropy.":[134],"High":[135],"leads":[137],"direct":[140],"top-K":[141],"Familiarity":[142],"path,":[144,155],"while":[145],"low":[146],"activates":[148],"Recollection":[150,154],"path.":[151],"In":[152],"system":[157],"clusters":[158],"candidate":[159],"memories":[160],"applies":[162],"alpha-mix":[163],"with":[164],"query":[166],"iteratively":[168],"expand":[169],"evidence":[170],"in":[171,224],"embedding":[172],"space,":[173],"simulating":[174],"deliberate":[175],"contextual":[176],"reconstruction.":[177],"This":[178],"design":[179],"embeds":[180],"human-like":[181],"dual-process":[182],"recognition":[183],"retriever,":[186],"avoiding":[187],"full-context":[188,211],"overhead":[189],"scalable,":[192],"adaptive":[193],"personalization.":[194],"Experiments":[195],"across":[196],"three":[197],"benchmarks":[198],"corpus":[200],"scales":[201],"demonstrate":[202],"consistently":[205],"outperforms":[206],"reasoning":[212],"under":[213],"fixed":[214],"budget":[215],"latency":[217],"constraints.":[218],"Our":[219],"code":[220],"can":[221],"be":[222],"found":[223],"Reproducibility":[226],"Statement.":[227]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-12T00:00:00"}