{"id":"https://openalex.org/W4413040199","doi":"https://doi.org/10.3233/shti251039","title":"Efficient Training Corpus Retrieval for Large Language Model Fine Tuning: A Case Study in Cancer","display_name":"Efficient Training Corpus Retrieval for Large Language Model Fine Tuning: A Case Study in Cancer","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413040199","doi":"https://doi.org/10.3233/shti251039","pmid":"https://pubmed.ncbi.nlm.nih.gov/40776057"},"language":"en","primary_location":{"id":"doi:10.3233/shti251039","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251039","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti251039","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065790431","display_name":"Avisha Das","orcid":"https://orcid.org/0000-0002-5015-2665"},"institutions":[{"id":"https://openalex.org/I4210127938","display_name":"Mayo Clinic Hospital","ror":"https://ror.org/03660jn93","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099","https://openalex.org/I4210127938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Avisha Das","raw_affiliation_strings":["Mayo Clinic Arizona, Phoenix, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-5015-2665","affiliations":[{"raw_affiliation_string":"Mayo Clinic Arizona, Phoenix, AZ, USA","institution_ids":["https://openalex.org/I4210127938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003448047","display_name":"Chiamaka S Diala","orcid":"https://orcid.org/0009-0007-8004-1417"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chiamaka Diala","raw_affiliation_strings":["University of Texas Health Science Center, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Health Science Center, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068592358","display_name":"Guocai Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guocai Chen","raw_affiliation_strings":["University of Texas Health Science Center, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Health Science Center, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730695","display_name":"Zhao Li","orcid":"https://orcid.org/0000-0002-6154-9879"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Li","raw_affiliation_strings":["University of Texas Health Science Center, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Health Science Center, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761496","display_name":"Rongbin Li","orcid":"https://orcid.org/0000-0001-6246-5004"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rongbin Li","raw_affiliation_strings":["University of Texas Health Science Center, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Health Science Center, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004590467","display_name":"Omer Anjum","orcid":"https://orcid.org/0009-0006-9930-6596"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omer Anjum","raw_affiliation_strings":["University of Texas Health Science Center, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Health Science Center, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074176245","display_name":"Wenyun Zheng","orcid":"https://orcid.org/0000-0002-0535-9114"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Jim Zheng","raw_affiliation_strings":["University of Texas Health Science Center, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas Health Science Center, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5065790431"],"corresponding_institution_ids":["https://openalex.org/I4210127938"],"apc_list":null,"apc_paid":null,"fwci":4.1459,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93892282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"329","issue":null,"first_page":"1251","last_page":"1255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.921999990940094,"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":0.921999990940094,"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/computer-science","display_name":"Computer science","score":0.7487800121307373},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5965235829353333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5660892724990845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5020511150360107},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4823710024356842},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3781123459339142},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3212684392929077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487800121307373},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5965235829353333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5660892724990845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5020511150360107},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4823710024356842},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3781123459339142},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3212684392929077},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001749","descriptor_name":"Urinary Bladder Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001749","descriptor_name":"Urinary Bladder Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001749","descriptor_name":"Urinary Bladder Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015850","descriptor_name":"Interleukin-6","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015850","descriptor_name":"Interleukin-6","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015850","descriptor_name":"Interleukin-6","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti251039","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251039","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:40776057","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40776057","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti251039","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti251039","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611"],"abstract_inverted_index":{"The":[0,94],"objective":[1],"is":[2],"to":[3,69],"create":[4],"an":[5],"automated":[6,50,122],"knowledge":[7,37,104,126],"extraction":[8],"tool":[9,51,62],"for":[10,18,40,75,124,149,153],"cancer":[11,29,41,132],"research":[12,42],"that":[13,52,117],"builds":[14],"high-quality":[15],"academic":[16,57,72],"corpora":[17,73],"LLM":[19],"fine-tuning":[20,76],"while":[21],"investigating":[22],"its":[23],"effectiveness":[24],"in":[25,36,111,131],"interleukin-6":[26],"and":[27,59,66,83,105,128,137,151],"bladder":[28,154],"domains.":[30],"To":[31],"address":[32],"the":[33,91,100,106],"current":[34],"gap":[35],"retrieval":[38,127],"techniques":[39],"data":[43],"collection,":[44],"we":[45],"propose":[46],"KnowledgePipeline,":[47],"a":[48,120,157],"novel":[49],"incorporates":[53],"diverse":[54],"aspects":[55],"of":[56,102,108,147],"papers":[58],"metadata.":[60],"Our":[61],"integrates":[63],"content,":[64],"co-citations,":[65],"co-authorship":[67],"networks":[68],"construct":[70],"domain-specific":[71,87,125],"suitable":[74],"LLMs.":[77],"We":[78,115],"leverage":[79],"two":[80],"LLMs":[81],"(GPTJ-6.7B":[82],"Galactica30B)":[84],"trained":[85],"on":[86,98],"question-answer":[88],"pairs":[89],"from":[90],"refined":[92],"data.":[93],"system's":[95],"evaluation":[96],"focuses":[97],"both":[99],"quality":[101],"extracted":[103],"performance":[107],"fine-tuned":[109,129,158],"models":[110],"open-ended":[112],"question-answering":[113],"tasks.":[114],"see":[116],"KnowledgePipeline":[118],"offers":[119],"scalable,":[121],"framework":[123],"applications":[130],"research,":[133],"advancing":[134],"literature":[135],"discovery":[136],"addressing":[138],"critical":[139],"biomedical":[140],"challenges.":[141],"It":[142],"achieved":[143],"high":[144],"relevance":[145],"scores":[146],"68%":[148],"IL-6":[150],"74.5%":[152],"cancer,":[155],"with":[156],"Galactica-30B":[159],"model":[160],"demonstrating":[161],"promising":[162],"capabilities.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
