{"id":"https://openalex.org/W4386815496","doi":"https://doi.org/10.14428/esann/2023.es2023-152","title":"Fine-tuning is not (always) overfitting artifacts","display_name":"Fine-tuning is not (always) overfitting artifacts","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386815496","doi":"https://doi.org/10.14428/esann/2023.es2023-152"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2023.es2023-152","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-152","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-152","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2023.es2023-152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032371887","display_name":"J\u00e9r\u00e9mie Bogaert","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"J\u00e9r\u00e9mie Bogaert","raw_affiliation_strings":["ICTEAM/UCLouvain -Belgium"],"affiliations":[{"raw_affiliation_string":"ICTEAM/UCLouvain -Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092891771","display_name":"Emmanuel Jean","orcid":"https://orcid.org/0009-0004-1544-7080"},"institutions":[{"id":"https://openalex.org/I4210143459","display_name":"Multitel","ror":"https://ror.org/042e7c302","country_code":"BE","type":"facility","lineage":["https://openalex.org/I4210143459"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Emmanuel Jean","raw_affiliation_strings":["Multitel -Belgium"],"affiliations":[{"raw_affiliation_string":"Multitel -Belgium","institution_ids":["https://openalex.org/I4210143459"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070860957","display_name":"Cyril de Bodt","orcid":"https://orcid.org/0000-0003-2347-1756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cyril de Bodt","raw_affiliation_strings":["ICTEAM/UCLouvain -Belgium"],"affiliations":[{"raw_affiliation_string":"ICTEAM/UCLouvain -Belgium","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070542865","display_name":"Fran\u00e7ois\u2010Xavier Standaert","orcid":"https://orcid.org/0000-0001-7444-0285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois-Xavier Standaert","raw_affiliation_strings":["ICTEAM/UCLouvain -Belgium"],"affiliations":[{"raw_affiliation_string":"ICTEAM/UCLouvain -Belgium","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032371887"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1758,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56919795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9955999851226807,"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/interpretability","display_name":"Interpretability","score":0.8469023704528809},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8348610997200012},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.8297274112701416},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.756028413772583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261252999305725},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.6273139715194702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5878287553787231},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5163310766220093},{"id":"https://openalex.org/keywords/white-spaces","display_name":"White spaces","score":0.45412319898605347},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41853514313697815},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12573695182800293},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09330800175666809},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09238997101783752},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08551448583602905},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07755371928215027}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8469023704528809},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8348610997200012},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8297274112701416},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.756028413772583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261252999305725},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.6273139715194702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5878287553787231},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5163310766220093},{"id":"https://openalex.org/C96391052","wikidata":"https://www.wikidata.org/wiki/Q256313","display_name":"White spaces","level":4,"score":0.45412319898605347},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41853514313697815},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12573695182800293},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09330800175666809},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09238997101783752},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08551448583602905},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07755371928215027},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C149946192","wikidata":"https://www.wikidata.org/wiki/Q3235733","display_name":"Cognitive radio","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14428/esann/2023.es2023-152","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-152","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-152","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},{"id":"pmh:oai:dial.uclouvain.be:boreal:279563","is_oa":true,"landing_page_url":"http://hdl.handle.net/2078.1/279563","pdf_url":null,"source":{"id":"https://openalex.org/S4306401902","display_name":"Digital Access to Libraries (Universit\u00e9 catholique de Louvain (UCL), l'Universit\u00e9 de Namur (UNamur) and the Universit\u00e9 Saint-Louis (USL-B))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I95674353","host_organization_name":"UCLouvain","host_organization_lineage":["https://openalex.org/I95674353"],"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":"ESANN proceedings, Vol. 1, no.1, p. 1-6 (2023)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.14428/esann/2023.es2023-152","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2023.es2023-152","pdf_url":"https://doi.org/10.14428/esann/2023.es2023-152","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2023 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7072270819","display_name":null,"funder_award_id":"2010235","funder_id":"https://openalex.org/F4320325905","funder_display_name":"Service Public de Wallonie"}],"funders":[{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"},{"id":"https://openalex.org/F4320325905","display_name":"Service Public de Wallonie","ror":"https://ror.org/0215gxf82"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386815496.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2951286828","https://openalex.org/W2962736243","https://openalex.org/W2964303116","https://openalex.org/W2965373594","https://openalex.org/W2970120757","https://openalex.org/W2970352191","https://openalex.org/W2986154550","https://openalex.org/W2996428491","https://openalex.org/W3103368673","https://openalex.org/W3117818268","https://openalex.org/W3176196997","https://openalex.org/W4287112659","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W2905433371","https://openalex.org/W4297676672","https://openalex.org/W3213778312","https://openalex.org/W3094152627","https://openalex.org/W4287633642","https://openalex.org/W3126822054","https://openalex.org/W3201490839","https://openalex.org/W4286980382"],"abstract_inverted_index":{"Since":[0],"their":[1,59],"release,":[2],"transformers,":[3,35],"and":[4,29,53,62,97],"in":[5,56,76],"particular":[6],"fine-tuned":[7,52,126],"transformers":[8],"are":[9,36,90],"widely":[10],"used":[11],"for":[12],"text":[13],"related":[14],"classification":[15,95],"tasks.":[16],"However,":[17],"only":[18],"a":[19,44,71,109],"few":[20],"studies":[21],"try":[22],"to":[23,49,93],"understand":[24],"how":[25],"fine-tuning":[26,69],"actually":[27],"works":[28],"existing":[30],"alternatives,":[31],"such":[32],"as":[33],"feature-based":[34,54],"often":[37],"overlooked.":[38],"In":[39],"this":[40],"work,":[41],"we":[42],"study":[43],"French":[45],"transformer":[46],"model,":[47],"CamemBERT,":[48],"compare":[50],"the":[51,83,94,102,105,113,122],"approaches":[55],"terms":[57],"of":[58,104,112,125],"performances,":[60],"interpretability":[61],"embedding":[63,98],"space.":[64],"We":[65,115],"observe":[66],"that":[67,89],"while":[68],"has":[70],"limited":[72],"impact":[73],"on":[74],"performances":[75],"our":[77],"case":[78],"study,":[79],"it":[80],"significantly":[81],"affects":[82],"intepretability":[84],"(by":[85,100],"better":[86],"isolating":[87],"words":[88],"intuitively":[91],"connected":[92],"task)":[96],"space":[99],"summarizing":[101],"majority":[103],"relevant":[106],"information":[107],"into":[108],"fewer":[110],"dimensions)":[111],"results.":[114],"conclude":[116],"by":[117],"highlighting":[118],"open":[119],"questions":[120],"regarding":[121],"generalization":[123],"potential":[124],"embeddings.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}