{"id":"https://openalex.org/W4412377138","doi":"https://doi.org/10.1145/3726302.3730178","title":"Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M","display_name":"Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377138","doi":"https://doi.org/10.1145/3726302.3730178"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730178","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730178","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730178","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102846109","display_name":"Dario Di Palma","orcid":"https://orcid.org/0009-0007-3593-7441"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Dario Di Palma","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0009-0007-3593-7441","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067588342","display_name":"Felice Antonio Merra","orcid":"https://orcid.org/0009-0003-8429-3487"},"institutions":[{"id":"https://openalex.org/I4210166865","display_name":"Institute of Cognitive Sciences and Technologies","ror":"https://ror.org/05w9g2j85","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210166865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Felice Antonio Merra","raw_affiliation_strings":["Cognism, Remote, Italy"],"raw_orcid":"https://orcid.org/0009-0003-8429-3487","affiliations":[{"raw_affiliation_string":"Cognism, Remote, Italy","institution_ids":["https://openalex.org/I4210166865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118969180","display_name":"Maurizio Sfilio","orcid":null},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maurizio Sfilio","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0009-0003-6902-3737","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072475963","display_name":"Vito Walter Anelli","orcid":"https://orcid.org/0000-0002-5567-4307"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vito Walter Anelli","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5567-4307","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076295894","display_name":"Fedelucio Narducci","orcid":"https://orcid.org/0000-0002-9255-3256"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fedelucio Narducci","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9255-3256","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034668928","display_name":"Tommaso Di Noia","orcid":"https://orcid.org/0000-0002-0939-5462"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tommaso Di Noia","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0939-5462","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.5125,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98882907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2582","last_page":"2586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9828000068664551,"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/T10028","display_name":"Topic Modeling","score":0.9807000160217285,"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/movielens","display_name":"MovieLens","score":0.9526665210723877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6000581383705139},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.592406153678894},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.2959996461868286},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.28345799446105957},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15587112307548523},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.09665486216545105},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.08845537900924683}],"concepts":[{"id":"https://openalex.org/C2776156558","wikidata":"https://www.wikidata.org/wiki/Q4353746","display_name":"MovieLens","level":4,"score":0.9526665210723877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000581383705139},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.592406153678894},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2959996461868286},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28345799446105957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15587112307548523},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.09665486216545105},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.08845537900924683}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730178","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730178","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730178","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.10212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10212","pdf_url":"https://arxiv.org/pdf/2505.10212","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730178","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730178","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730178","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3478515953","display_name":null,"funder_award_id":"CN00000023","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4508289328","display_name":null,"funder_award_id":"PE00000013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G45605271","display_name":null,"funder_award_id":"CUP: D93C22000410001","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8829736464","display_name":null,"funder_award_id":"1033 17/06/2022","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377138.pdf","grobid_xml":"https://content.openalex.org/works/W4412377138.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2011700584","https://openalex.org/W2140310134","https://openalex.org/W2161171125","https://openalex.org/W3134330728","https://openalex.org/W4367694290","https://openalex.org/W4368755500","https://openalex.org/W4381569294","https://openalex.org/W4386728933","https://openalex.org/W4388327547","https://openalex.org/W4389762725","https://openalex.org/W4390041455","https://openalex.org/W4390306635","https://openalex.org/W4393156838","https://openalex.org/W4393300184","https://openalex.org/W4394744221","https://openalex.org/W4396734745","https://openalex.org/W4400524564","https://openalex.org/W4400528558","https://openalex.org/W4403220034","https://openalex.org/W4403220611","https://openalex.org/W4403220878","https://openalex.org/W4403221563","https://openalex.org/W4403577794","https://openalex.org/W4408981098","https://openalex.org/W6682887400","https://openalex.org/W6781551161"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2398491113","https://openalex.org/W4400199659","https://openalex.org/W4384919653","https://openalex.org/W2794657157","https://openalex.org/W2219888463","https://openalex.org/W3045147512","https://openalex.org/W2022984797"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,43],"become":[5],"increasingly":[6],"central":[7],"to":[8,12,39,74],"recommendation":[9,32,46],"scenarios":[10],"due":[11],"their":[13,51],"remarkable":[14],"natural":[15],"language":[16],"understanding":[17],"and":[18],"generation":[19],"capabilities.":[20],"Although":[21],"significant":[22],"research":[23,63],"has":[24,36],"explored":[25],"the":[26,60],"use":[27],"of":[28,50,62],"LLMs":[29],"for":[30,82],"various":[31],"tasks,":[33],"little":[34],"effort":[35],"been":[37],"dedicated":[38],"verifying":[40],"whether":[41],"they":[42],"memorized":[44,68],"public":[45],"dataset":[47],"as":[48,65],"part":[49],"training":[52],"data.":[53],"This":[54],"is":[55],"undesirable":[56],"because":[57],"memorization":[58,78],"reduces":[59],"generalizability":[61],"findings,":[64],"benchmarking":[66],"on":[67],"datasets":[69],"does":[70],"not":[71],"guarantee":[72],"generalization":[73],"unseen":[75],"datasets.":[76],"Furthermore,":[77],"can":[79],"amplify":[80],"biases,":[81],"example,":[83],"some":[84],"popular":[85],"items":[86],"may":[87],"be":[88],"recommended":[89],"more":[90],"frequently":[91],"than":[92],"others.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
