{"id":"https://openalex.org/W4412215438","doi":null,"title":"LLM Fine-Tuning With Biomedical Open-Source Data","display_name":"LLM Fine-Tuning With Biomedical Open-Source Data","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4412215438"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:openaire/dfe4f8b7-460e-421b-b65d-e271c73a50ea","doi":null,"is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/dfe4f8b7-460e-421b-b65d-e271c73a50ea","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anaya, C, Fernandes, M & Couto, F M 2024, 'LLM Fine-Tuning With Biomedical Open-Source Data', CEUR Workshop Proceedings, vol. 3740, pp. 68-77.","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://researchprofiles.ku.dk/da/publications/dfe4f8b7-460e-421b-b65d-e271c73a50ea","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118946849","display_name":"Christopher Anaya","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anaya, Christopher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055005781","display_name":"Maria Fernandes","orcid":"https://orcid.org/0000-0002-8733-1018","observed_orcids":["https://orcid.org/0000-0002-8733-1018"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]},{"id":"https://openalex.org/I4391767703","display_name":"Novo Nordisk Foundation Center for Basic Metabolic Research","ror":"https://ror.org/02s32fb62","country_code":"DK","type":"other","lineage":["https://openalex.org/I124055696","https://openalex.org/I4391767703"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Fernandes, Maria; id_orcid 0000-0002-8733-1018","raw_affiliation_strings":["K\u00f8benhavns Universitet, Faculty of Health and Medical Sciences, Novo Nordisk Foundation Center for Basic Metabolic Research, Merino Group, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"K\u00f8benhavns Universitet, Faculty of Health and Medical Sciences, Novo Nordisk Foundation Center for Basic Metabolic Research, Merino Group, DK","institution_ids":["https://openalex.org/I124055696","https://openalex.org/I4391767703"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014333753","display_name":"Francisco M. Couto","orcid":"https://orcid.org/0000-0003-0627-1496","observed_orcids":["https://orcid.org/0000-0003-0627-1496"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Couto, Francisco M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26426713,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4343000054359436,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4343000054359436,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.41359999775886536,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.03519999980926514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/biomedical-question-answering","display_name":"biomedical question answering","score":0.996999979019165},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.859000027179718},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.9850000143051147},{"id":"https://openalex.org/keywords/qlora","display_name":"QLoRA","score":0.9869999885559082},{"id":"https://openalex.org/keywords/bioasq","display_name":"BioASQ","score":0.7649999856948853},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.734000027179718},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.6579999923706055},{"id":"https://openalex.org/keywords/mistral-7b-instruct","display_name":"Mistral-7B-Instruct","score":0.8069999814033508},{"id":"https://openalex.org/keywords/gene-ontology","display_name":"Gene Ontology","score":0.7250000238418579},{"id":"https://openalex.org/keywords/drugbank","display_name":"DrugBank","score":0.9760000109672546},{"id":"https://openalex.org/keywords/factoid-questions","display_name":"factoid questions","score":0.597000002861023},{"id":"https://openalex.org/keywords/polar-questions","display_name":"yes-no questions","score":0.7049999833106995}],"concepts":[{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.7255122661590576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4151685833930969},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3636168837547302},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19284820556640625},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06650179624557495}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:pure.atira.dk:openaire/dfe4f8b7-460e-421b-b65d-e271c73a50ea","doi":null,"is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/dfe4f8b7-460e-421b-b65d-e271c73a50ea","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anaya, C, Fernandes, M & Couto, F M 2024, 'LLM Fine-Tuning With Biomedical Open-Source Data', CEUR Workshop Proceedings, vol. 3740, pp. 68-77.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:repositorio.ulisboa.pt:10400.5/116644","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10400.5/116644","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"master thesis"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/dfe4f8b7-460e-421b-b65d-e271c73a50ea","doi":null,"is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/dfe4f8b7-460e-421b-b65d-e271c73a50ea","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anaya, C, Fernandes, M & Couto, F M 2024, 'LLM Fine-Tuning With Biomedical Open-Source Data', CEUR Workshop Proceedings, vol. 3740, pp. 68-77.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1759428316","display_name":"LASIGE - Extreme Computing","funder_award_id":"UIDP/00408/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2089664753","display_name":"LASIGE - Extreme Computing","funder_award_id":"UIDB/00408/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G4230908485","display_name":null,"funder_award_id":"NNF23SA\u00a00084103","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G4504918650","display_name":null,"funder_award_id":"NNF 18 CC0034900","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G6997658380","display_name":null,"funder_award_id":"10.54499","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8221995800","display_name":null,"funder_award_id":"NNF23SA0084103","funder_id":"https://openalex.org/F4320322436","funder_display_name":"Novo Nordisk"},{"id":"https://openalex.org/G8351935874","display_name":null,"funder_award_id":"NNF18CC0034900","funder_id":"https://openalex.org/F4320322436","funder_display_name":"Novo Nordisk"}],"funders":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"},{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402701735","https://openalex.org/W4414158632","https://openalex.org/W4409190866","https://openalex.org/W7155180851","https://openalex.org/W4416192983","https://openalex.org/W4409235791","https://openalex.org/W4394591920","https://openalex.org/W4406458100","https://openalex.org/W4417098914","https://openalex.org/W4391973028"],"abstract_inverted_index":{"Biomedical":[0],"question":[1,131,172],"answering":[2],"(QA)":[3],"systems":[4],"aim":[5],"to":[6,16,42,64,133,225,267],"support":[7],"researchers":[8],"and":[9,48,84,94,137,159,208,217,246,262,272],"clinicians":[10],"by":[11,154,221],"providing":[12],"accurate,":[13],"context-aware":[14],"answers":[15],"complex":[17],"information":[18],"needs.":[19],"Recent":[20],"advances":[21],"in":[22,37],"large":[23],"language":[24],"models":[25],"(LLMs)":[26],"have":[27],"significantly":[28],"improved":[29,263],"QA":[30,92,249],"performance":[31,170],"across":[32,171],"domains,":[33],"yet":[34],"challenges":[35],"remain":[36],"the":[38,49,58,72,98,118,150,165,195,204,268],"biomedical":[39,68,91,248,260],"domain":[40],"due":[41],"terminology":[43],"complexity,":[44],"limited":[45],"data":[46],"availability,":[47],"risk":[50],"of":[51,60,90,101,181,259,270],"generating":[52],"hallucinated":[53],"content.":[54],"This":[55],"thesis":[56,105],"investigates":[57],"application":[59],"parameter-efficient":[61],"fine-tuning":[62,108,238],"techniques":[63],"adapt":[65],"LLMs":[66],"for":[67,116,129,175,243],"QA,":[69],"focusing":[70],"on":[71,111,145],"BioASQ":[73],"challenge":[74],"Task":[75],"B":[76],"Phase":[77],"B,":[78],"which":[79],"includes":[80],"yes/no,":[81],"factoid,":[82],"list,":[83],"ideal":[85,192],"questions.":[86],"A":[87],"comprehensive":[88],"review":[89],"datasets":[93],"LLM":[95],"adaptations":[96],"highlights":[97],"evolving":[99],"landscape":[100],"knowledge-infused":[102],"models.":[103],"The":[104,140,229],"presents":[106],"a":[107,113,146,240],"pipeline":[109],"based":[110],"QLoRA,":[112],"memory-efficient":[114],"method":[115],"adapting":[117],"Mistral-7B-Instruct-v0.1":[119],"model":[120],"using":[121],"quantized":[122],"weights.":[123],"Domain-specific":[124],"prompt":[125],"templates":[126],"were":[127,219],"designed":[128],"each":[130],"type":[132],"optimize":[134],"answer":[135],"formatting":[136],"reduce":[138],"hallucinations.":[139],"experimental":[141],"setup":[142],"included":[143],"training":[144,151],"curated":[147],"dataset":[148,152],"comprising":[149],"provided":[153],"BioASQ,":[155],"Gene":[156],"Ontology,":[157],"DrugBank,":[158],"BiQA-derived":[160],"examples.":[161],"Results":[162],"show":[163],"that":[164,232],"proposed":[166],"system":[167,196,227],"achieves":[168],"competitive":[169],"types,":[173],"particularly":[174],"yes/no":[176],"questions,":[177,194],"attaining":[178],"F1":[179],"scores":[180],"0.76,":[182],"where":[183],"structured":[184],"JSON":[185],"outputs":[186],"enabled":[187],"reliable":[188],"automatic":[189],"evaluation.":[190],"For":[191],"(free-text)":[193],"demonstrated":[197],"fluent":[198],"but":[199],"occasionally":[200],"speculative":[201],"responses,":[202],"highlighting":[203],"trade-offs":[205],"between":[206],"informativeness":[207],"factual":[209],"grounding.":[210],"Evaluation":[211],"metrics":[212],"such":[213],"as":[214],"F1,":[215],"MRR,":[216],"ROUGE":[218],"complemented":[220],"qualitative":[222],"error":[223],"analysis":[224],"assess":[226],"robustness.":[228],"study":[230],"concludes":[231],"combining":[233],"domain-adapted":[234],"prompts":[235],"with":[236],"QLoRA":[237],"offers":[239],"promising":[241],"approach":[242],"deploying":[244],"efficient":[245],"effective":[247],"systems.":[250],"Future":[251],"work":[252],"should":[253],"explore":[254],"retrieval-augmented":[255],"generation,":[256],"deeper":[257],"integration":[258],"ontologies,":[261],"evaluation":[264],"frameworks":[265],"tailored":[266],"nuances":[269],"clinical":[271],"research":[273],"settings.":[274]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-07-11T00:00:00"}