{"id":"https://openalex.org/W4415428108","doi":"https://doi.org/10.3233/faia251323","title":"Predicting Memorization Within Large Language Models Fine-Tuned for Classification","display_name":"Predicting Memorization Within Large Language Models Fine-Tuned for Classification","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428108","doi":"https://doi.org/10.3233/faia251323"},"language":null,"primary_location":{"id":"doi:10.3233/faia251323","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251323","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251323","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099054966","display_name":"J\u00e9r\u00e9mie Dentan","orcid":"https://orcid.org/0009-0001-5561-8030"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J\u00e9r\u00e9mie Dentan","raw_affiliation_strings":["LIX (\u00c9cole Polytechnique, IP Paris, CNRS)"],"raw_orcid":"https://orcid.org/0009-0001-5561-8030","affiliations":[{"raw_affiliation_string":"LIX (\u00c9cole Polytechnique, IP Paris, CNRS)","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051885442","display_name":"Davide Buscaldi","orcid":"https://orcid.org/0000-0003-1112-3789"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I51101395","display_name":"Universit\u00e9 Paris 1 Panth\u00e9on-Sorbonne","ror":"https://ror.org/002t25c44","country_code":"FR","type":"education","lineage":["https://openalex.org/I51101395"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Davide Buscaldi","raw_affiliation_strings":["LIPN (Universit\u00e9 Sorbonne Paris Nord)","LIX (\u00c9cole Polytechnique, IP Paris, CNRS)"],"raw_orcid":"https://orcid.org/0000-0003-1112-3789","affiliations":[{"raw_affiliation_string":"LIPN (Universit\u00e9 Sorbonne Paris Nord)","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I51101395","https://openalex.org/I4210091279"]},{"raw_affiliation_string":"LIX (\u00c9cole Polytechnique, IP Paris, CNRS)","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052180718","display_name":"Aymen Shabou","orcid":"https://orcid.org/0000-0001-8933-7053"},"institutions":[{"id":"https://openalex.org/I80201079","display_name":"Credit Suisse (Switzerland)","ror":"https://ror.org/05h634p83","country_code":"CH","type":"company","lineage":["https://openalex.org/I80201079"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Aymen Shabou","raw_affiliation_strings":["Cr\u00e9dit Agricole SA"],"raw_orcid":"https://orcid.org/0000-0001-8933-7053","affiliations":[{"raw_affiliation_string":"Cr\u00e9dit Agricole SA","institution_ids":["https://openalex.org/I80201079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031988385","display_name":"Sonia Haddad-Vanier","orcid":"https://orcid.org/0000-0001-6390-8882"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sonia Vanier","raw_affiliation_strings":["LIX (\u00c9cole Polytechnique, IP Paris, CNRS)"],"raw_orcid":"https://orcid.org/0000-0001-6390-8882","affiliations":[{"raw_affiliation_string":"LIX (\u00c9cole Polytechnique, IP Paris, CNRS)","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.43866356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9218000173568726,"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":0.9218000173568726,"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/memorization","display_name":"Memorization","score":0.6970999836921692},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6322000026702881},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6129999756813049},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6021999716758728},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5821999907493591},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5152000188827515},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41609999537467957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704800009727478},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.6970999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6383000016212463},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6322000026702881},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6129999756813049},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5881999731063843},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2776889888","wikidata":"https://www.wikidata.org/wiki/Q1135789","display_name":"Unintended consequences","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251323","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251323","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251323","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251323","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"have":[3],"received":[4],"significant":[5,24],"attention":[6],"due":[7],"to":[8,11,47,79,104],"their":[9,27],"abilities":[10],"solve":[12],"a":[13,23,31,67,76,83,125],"wide":[14],"range":[15],"of":[16,26,57,99,143],"complex":[17],"tasks.":[18,90],"However":[19],"these":[20],"models":[21,112],"memorize":[22],"proportion":[25],"training":[28,100,110],"data,":[29],"posing":[30],"serious":[32],"threat":[33],"when":[34],"disclosed":[35],"at":[36],"inference":[37],"time.":[38],"To":[39,70],"mitigate":[40],"this":[41,72],"unintended":[42],"memorization,":[43],"it":[44],"is":[45,59,93,117],"crucial":[46],"understand":[48],"what":[49],"elements":[50],"are":[51,148],"memorized":[52,81],"and":[53,101,123,141],"why.":[54],"This":[55,91],"area":[56],"research":[58],"largely":[60],"unexplored,":[61],"with":[62],"most":[63],"existing":[64],"works":[65],"providing":[66],"posteriori":[68],"explanations.":[69],"address":[71],"gap,":[73],"we":[74],"propose":[75],"new":[77,120],"approach":[78],"detect":[80],"samples":[82,145],"priori":[84],"in":[85],"LLMs":[86],"fine-tuned":[87],"for":[88,137],"classification":[89,106],"method":[92,116],"effective":[94],"from":[95,113],"the":[96,135,138],"early":[97],"stages":[98],"readily":[102],"adaptable":[103],"other":[105],"settings,":[107],"such":[108],"as":[109],"vision":[111],"scratch.":[114],"Our":[115],"supported":[118],"by":[119],"theoretical":[121],"results,":[122,133],"requires":[124],"low":[126],"computational":[127],"budget.":[128],"We":[129],"achieve":[130],"strong":[131],"empirical":[132],"paving":[134],"way":[136],"systematic":[139],"identification":[140],"protection":[142],"vulnerable":[144],"before":[146],"they":[147],"memorized.":[149]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}