{"id":"https://openalex.org/W7095020844","doi":null,"title":"D\u00e9tection des contaminations de LLM par extraction de donn\u00e9es : une revue de litt\u00e9rature pratique","display_name":"D\u00e9tection des contaminations de LLM par extraction de donn\u00e9es : une revue de litt\u00e9rature pratique","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W7095020844"},"language":"fr","primary_location":{"id":"pmh:oai:HAL:hal-05330614v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05330614v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"TALN 2025 - 32\u00e8me Conf\u00e9rence sur le Traitement Automatique des Langues Naturelles, Jul 2025, Marseille, France. pp.233-251","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05330614v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094244452","display_name":"Pierre Lepagnol","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lepagnol, Pierre","raw_affiliation_strings":["LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)","SCIAM [Paris] (10 rue de Penthievre,75008 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]},{"raw_affiliation_string":"SCIAM [Paris] (10 rue de Penthievre,75008 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062311074","display_name":"Thomas Gerald","orcid":"https://orcid.org/0000-0001-7510-9690","observed_orcids":["https://orcid.org/0000-0001-7510-9690"]},"institutions":[{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gerald, Thomas","raw_affiliation_strings":["LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000557257","display_name":"Sahar Ghannay","orcid":"https://orcid.org/0000-0002-7531-2522","observed_orcids":["https://orcid.org/0000-0002-7531-2522"]},"institutions":[{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ghannay, Sahar","raw_affiliation_strings":["LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054392060","display_name":"Christophe Servan","orcid":"https://orcid.org/0000-0003-2306-7075","observed_orcids":["https://orcid.org/0000-0003-2306-7075"]},"institutions":[{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Servan, Christophe","raw_affiliation_strings":["LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rosset, S.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rosset, S.","raw_affiliation_strings":["LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507Rue du Belv\u00e9d\u00e8re91405 Orsay cedexet Campus Universitaire b\u00e2t 6401 rue Raimond Castaing91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4387152856"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34587149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0860000029206276,"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":0.0860000029206276,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.03449999913573265,"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/T13793","display_name":"Environmental and Analytical Chemistry Studies","score":0.03440000116825104,"subfield":{"id":"https://openalex.org/subfields/2312","display_name":"Water Science and Technology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.9580000042915344},{"id":"https://openalex.org/keywords/data-extraction","display_name":"data extraction","score":0.6710000038146973},{"id":"https://openalex.org/keywords/contaminant-detection","display_name":"contamination detection","score":0.6549999713897705},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.4740000069141388},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.3019999861717224}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.28360000252723694},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2590000033378601},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.1956000030040741},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.1834000051021576},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.17739999294281006},{"id":"https://openalex.org/C29456083","wikidata":"https://www.wikidata.org/wiki/Q1221899","display_name":"Gynecology","level":1,"score":0.17149999737739563},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.17020000517368317},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.16850000619888306},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.16459999978542328}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-05330614v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05330614v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"TALN 2025 - 32\u00e8me Conf\u00e9rence sur le Traitement Automatique des Langues Naturelles, Jul 2025, Marseille, France. pp.233-251","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05330614v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05330614v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"TALN 2025 - 32\u00e8me Conf\u00e9rence sur le Traitement Automatique des Langues Naturelles, Jul 2025, Marseille, France. pp.233-251","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166495070","https://openalex.org/W4411120124","https://openalex.org/W4403679014","https://openalex.org/W7166876690","https://openalex.org/W4385965989","https://openalex.org/W4402683841","https://openalex.org/W7027667564","https://openalex.org/W4415914389","https://openalex.org/W7167751889","https://openalex.org/W4410000117"],"abstract_inverted_index":{"Cet":[0],"\u00e9tat":[1],"de":[2,7,17,43,70,93,95,102,121,127,129],"l'art":[3],"examine":[4],"le":[5],"probl\u00e8me":[6],"la":[8,52,117,125],"contamination":[9,71,130],"des":[10,30,58],"donn\u00e9es":[11,31,94],"d'entra\u00eenement":[12],"dans":[13],"les":[14,25,83,90,97,100],"grands":[15],"mod\u00e8les":[16,26],"langue":[18],"(LLM).":[19],"Ce":[20],"ph\u00e9nom\u00e8ne":[21],"se":[22],"produit":[23],"lorsque":[24],"sont":[27],"\u00e9valu\u00e9s":[28],"sur":[29],"qu'ils":[32],"ont":[33],"d\u00e9j\u00e0":[34],"rencontr\u00e9es":[35],"durant":[36],"leur":[37],"entra\u00eenement,":[38],"cr\u00e9ant":[39],"une":[40,48,108],"fausse":[41],"impression":[42],"performance.":[44],"Cette":[45],"\u00e9tude":[46],"propose":[47],"synth\u00e8se":[49],"pratique":[50],"pour":[51,123],"communaut\u00e9":[53],"scientifique":[54],"du":[55],"traitement":[56],"automatique":[57],"langues":[59],"(TAL).":[60],"Nous":[61,87],"pr\u00e9sentons":[62],"un":[63],"cadre":[64],"d'analyse":[65],"qui":[66],"distingue":[67],"diff\u00e9rents":[68],"niveaux":[69],"ainsi":[72],"que":[73],"diff\u00e9rentes":[74],"m\u00e9thodes":[75,91,115],"class\u00e9es":[76],"selon":[77],"l'acc\u00e8s":[78],"au":[79],"mod\u00e8le":[80],"(White/Gray/BlackBox)":[81],"et":[82,104],"techniques":[84],"utilis\u00e9es":[85],"(Similarit\u00e9/Probabilit\u00e9/Extraction).":[86],"explorons":[88],"particuli\u00e8rement":[89],"d'extraction":[92],"LLM,":[96],"approches":[98],"techniques,":[99],"mesures":[101],"performance":[103],"leurs":[105],"limites.":[106],"Dans":[107],"perspective":[109],"pratique,":[110],"nous":[111],"avons":[112],"synth\u00e9tis\u00e9":[113],"ces":[114],"sous":[116],"forme":[118],"d'un":[119],"arbre":[120],"d\u00e9cision":[122],"s\u00e9lectionner":[124],"m\u00e9thode":[126],"d\u00e9tection":[128],"ad\u00e9quate.":[131]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2025-10-26T00:00:00"}
