{"id":"https://openalex.org/W7158480409","doi":"https://doi.org/10.48550/arxiv.2604.25920","title":"Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats","display_name":"Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7158480409","doi":"https://doi.org/10.48550/arxiv.2604.25920"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.25920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25920","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.25920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114284977","display_name":"Pierre Epron","orcid":null},"institutions":[{"id":"https://openalex.org/I2802827176","display_name":"Dignity Health","ror":"https://ror.org/05c9r4685","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2802827176"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Epron, Pierre","raw_affiliation_strings":["HeKA | U1346, DIG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HeKA | U1346, DIG","institution_ids":["https://openalex.org/I2802827176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082641159","display_name":"Adrien Coulet","orcid":"https://orcid.org/0000-0002-1466-062X"},"institutions":[{"id":"https://openalex.org/I4210132374","display_name":"Heureka (United States)","ror":"https://ror.org/02xvpd793","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Coulet, Adrien","raw_affiliation_strings":["HeKA | U1346"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HeKA | U1346","institution_ids":["https://openalex.org/I4210132374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009026163","display_name":"Mehwish Alam","orcid":"https://orcid.org/0000-0002-7867-6612"},"institutions":[{"id":"https://openalex.org/I4210130152","display_name":"Institut de Psychiatrie et Neurosciences de Paris","ror":"https://ror.org/02g40zn06","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I4210130152","https://openalex.org/I4210160774"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alam, Mehwish","raw_affiliation_strings":["IP Paris, DIG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IP Paris, DIG","institution_ids":["https://openalex.org/I4210130152"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10028","display_name":"Topic Modeling","score":0.7364000082015991,"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":0.7364000082015991,"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/T13629","display_name":"Text Readability and Simplification","score":0.06459999829530716,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.024299999698996544,"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/language-model","display_name":"Language model","score":0.5867000222206116},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5630999803543091},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.3935999870300293},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.38449999690055847},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.37619999051094055},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.36500000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087000250816345},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5867000222206116},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5630999803543091},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4706000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4147000014781952},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.37619999051094055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2599000036716461},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.25920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25920","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.25920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25920","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5499769449234009,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"their":[1,74],"strong":[2],"linguistic":[3],"capabilities,":[4],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"are":[9],"computationally":[10],"demanding":[11],"and":[12,23],"require":[13],"substantial":[14],"resources":[15],"for":[16,81],"fine-tuning,":[17],"which":[18],"is":[19],"unadapted":[20],"to":[21,69],"privacy":[22],"budget":[24],"constraints":[25],"of":[26,51],"many":[27,92],"healthcare":[28],"settings.":[29],"To":[30],"address":[31],"this,":[32],"we":[33,47],"present":[34],"an":[35],"experimental":[36],"analysis":[37,86],"focused":[38],"on":[39,55],"Biomedical":[40],"Named":[41],"Entity":[42],"Recognition":[43],"using":[44],"lightweight":[45,62,77],"LLMs,":[46],"evaluate":[48],"the":[49,70],"impact":[50],"different":[52],"output":[53],"formats":[54,94],"model":[56],"performance.":[57,107],"The":[58],"results":[59],"reveal":[60],"that":[61,88],"LLMs":[63],"can":[64],"achieve":[65],"competitive":[66],"performance":[67],"compared":[68],"larger":[71],"models,":[72],"highlighting":[73],"potential":[75],"as":[76],"yet":[78],"effective":[79],"alternatives":[80],"biomedical":[82],"information":[83],"extraction.":[84],"Our":[85],"shows":[87],"instruction":[89],"tuning":[90],"over":[91],"distinct":[93],"does":[95],"not":[96],"improve":[97],"performance,":[98],"but":[99],"identifies":[100],"several":[101],"format":[102],"consistently":[103],"associated":[104],"with":[105],"better":[106]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-01T00:00:00"}