{"id":"https://openalex.org/W4394973009","doi":"https://doi.org/10.48550/arxiv.2404.11672","title":"MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory","display_name":"MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory","publication_year":2024,"publication_date":"2024-04-17","ids":{"openalex":"https://openalex.org/W4394973009","doi":"https://doi.org/10.48550/arxiv.2404.11672"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2404.11672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.11672","pdf_url":"https://arxiv.org/pdf/2404.11672","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":"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.11672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100588790","display_name":"Ali Modarressi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Modarressi, Ali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110633837","display_name":"Abdullatif K\u00f6ksal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K\u00f6ksal, Abdullatif","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047234847","display_name":"Ayyoob Imani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Imani, Ayyoob","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031986521","display_name":"Mohsen Fayyaz","orcid":"https://orcid.org/0000-0001-5254-3128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fayyaz, Mohsen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071144367","display_name":"Hinrich Sch\u00fctze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sch\u00fctze, Hinrich","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100588790"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10320","display_name":"Neural Networks and Applications","score":0.9545000195503235,"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/T10320","display_name":"Neural Networks and Applications","score":0.9545000195503235,"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/computer-science","display_name":"Computer science","score":0.5143057107925415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5143057107925415}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2404.11672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.11672","pdf_url":"https://arxiv.org/pdf/2404.11672","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":"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.2404.11672","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.11672","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.11672","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.11672","pdf_url":"https://arxiv.org/pdf/2404.11672","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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394973009.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"While":[0],"current":[1],"large":[2],"language":[3,126],"models":[4],"(LLMs)":[5],"perform":[6],"well":[7],"on":[8,17],"many":[9],"knowledge-related":[10],"tasks,":[11],"they":[12,28],"are":[13,68],"limited":[14],"by":[15,84,98],"relying":[16],"their":[18,37],"parameters":[19,64],"as":[20,39,138],"an":[21,139],"implicit":[22],"storage":[23],"mechanism.":[24],"As":[25],"a":[26,78,86],"result,":[27],"struggle":[29],"with":[30,35,63,102],"memorizing":[31],"rare":[32],"events":[33],"and":[34,60,88,105,123,130,147],"updating":[36],"memory":[38,51,67,91,104,150],"facts":[40],"change":[41],"over":[42],"time.":[43],"In":[44,72],"addition,":[45],"the":[46,95,103,107,120],"uninterpretable":[47],"nature":[48],"of":[49,81],"parametric":[50],"makes":[52],"it":[53],"challenging":[54],"to":[55],"prevent":[56],"hallucination.":[57],"Model":[58],"editing":[59],"augmenting":[61],"LLMs":[62,83,144],"specialized":[65],"for":[66],"only":[69],"partial":[70],"solutions.":[71],"this":[73],"paper,":[74],"we":[75],"introduce":[76],"MemLLM,":[77],"novel":[79],"method":[80],"enhancing":[82],"integrating":[85],"structured":[87],"explicit":[89],"read-and-write":[90],"module.":[92],"MemLLM":[93,118,137],"tackles":[94],"aforementioned":[96],"challenges":[97],"enabling":[99],"dynamic":[100],"interaction":[101],"improving":[106],"LLM's":[108,121],"capabilities":[109],"in":[110,125,128,133],"using":[111],"stored":[112],"knowledge.":[113],"Our":[114],"experiments":[115],"indicate":[116],"that":[117],"enhances":[119],"performance":[122],"interpretability,":[124],"modeling":[127],"general":[129],"knowledge-intensive":[131],"tasks":[132],"particular.":[134],"We":[135],"see":[136],"important":[140],"step":[141],"towards":[142],"making":[143],"more":[145],"grounded":[146],"factual":[148],"through":[149],"augmentation.":[151],"The":[152],"project":[153],"repository":[154],"is":[155],"publicly":[156],"available":[157],"at":[158],"https://github.com/amodaresi/MemLLM":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}