{"id":"https://openalex.org/W4412567144","doi":"https://doi.org/10.1109/access.2025.3591739","title":"Data-Centric Fine-Tuning of Small Language Models for Automatic Extraction of Technical Requirements","display_name":"Data-Centric Fine-Tuning of Small Language Models for Automatic Extraction of Technical Requirements","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412567144","doi":"https://doi.org/10.1109/access.2025.3591739"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3591739","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591739","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3591739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112200335","display_name":"Leopold M\u00fcller","orcid":"https://orcid.org/0009-0008-9968-8103"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leopold M\u00fcller","raw_affiliation_strings":["Information Systems and Human-Centric Artificial Intelligence, University of Bayreuth, Bayreuth, Germany","University of Bayreuth, Universitätsstraße 30, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0009-0008-9968-8103","affiliations":[{"raw_affiliation_string":"Information Systems and Human-Centric Artificial Intelligence, University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]},{"raw_affiliation_string":"University of Bayreuth, Universitätsstraße 30, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nina Schwarz","orcid":"https://orcid.org/0009-0005-0835-035X"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nina Schwarz","raw_affiliation_strings":["Fraunhofer FIT, Bayreuth, Germany","Fraunhofer FIT, Wittelsbachering 10, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0009-0005-0835-035X","affiliations":[{"raw_affiliation_string":"Fraunhofer FIT, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210110507"]},{"raw_affiliation_string":"Fraunhofer FIT, Wittelsbachering 10, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210110507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114438799","display_name":"Lars B\u00f6cking","orcid":null},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars B\u00f6cking","raw_affiliation_strings":["Information Systems and Human-Centric Artificial Intelligence, University of Bayreuth, Bayreuth, Germany","University of Bayreuth, Universitätsstraße 30, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0009-0009-1365-7224","affiliations":[{"raw_affiliation_string":"Information Systems and Human-Centric Artificial Intelligence, University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]},{"raw_affiliation_string":"University of Bayreuth, Universitätsstraße 30, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119042045","display_name":"Andreas Bereczuk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093774","display_name":"Tennet (Germany)","ror":"https://ror.org/00khe8x73","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093774"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Bereczuk","raw_affiliation_strings":["TenneT TSO GmbH, Bayreuth, Germany","TenneT TSO GmbH, Berneckerstraße 70, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4167-1225","affiliations":[{"raw_affiliation_string":"TenneT TSO GmbH, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210093774"]},{"raw_affiliation_string":"TenneT TSO GmbH, Berneckerstraße 70, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210093774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089398444","display_name":"Hanno Stagge","orcid":"https://orcid.org/0000-0002-0275-9489"},"institutions":[{"id":"https://openalex.org/I4210093774","display_name":"Tennet (Germany)","ror":"https://ror.org/00khe8x73","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093774"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hanno Stagge","raw_affiliation_strings":["TenneT TSO GmbH, Bayreuth, Germany","TenneT TSO GmbH, Berneckerstraße 70, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0275-9489","affiliations":[{"raw_affiliation_string":"TenneT TSO GmbH, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210093774"]},{"raw_affiliation_string":"TenneT TSO GmbH, Berneckerstraße 70, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210093774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014929985","display_name":"Wolfgang Kratsch","orcid":"https://orcid.org/0000-0001-9815-0653"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Kratsch","raw_affiliation_strings":["Fraunhofer FIT, Bayreuth, Germany","Fraunhofer FIT, Wittelsbachering 10, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9815-0653","affiliations":[{"raw_affiliation_string":"Fraunhofer FIT, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210110507"]},{"raw_affiliation_string":"Fraunhofer FIT, Wittelsbachering 10, Bayreuth, Germany","institution_ids":["https://openalex.org/I4210110507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071819311","display_name":"Niklas K\u00fchl","orcid":"https://orcid.org/0000-0001-6750-0876"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Niklas K\u00fchl","raw_affiliation_strings":["Information Systems and Human-Centric Artificial Intelligence, University of Bayreuth, Bayreuth, Germany","University of Bayreuth, Universitätsstraße 30, Bayreuth, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6750-0876","affiliations":[{"raw_affiliation_string":"Information Systems and Human-Centric Artificial Intelligence, University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]},{"raw_affiliation_string":"University of Bayreuth, Universitätsstraße 30, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.4655,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94402041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"135301","last_page":"135315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9074000120162964,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9074000120162964,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045233488082886},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4903988838195801},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.4801296889781952},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.463215172290802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3536792993545532},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3506990671157837},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2689186930656433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045233488082886},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4903988838195801},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.4801296889781952},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.463215172290802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3536792993545532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3506990671157837},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2689186930656433},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3591739","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591739","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:822448e261f348b488248255127e478c","is_oa":true,"landing_page_url":"https://doaj.org/article/822448e261f348b488248255127e478c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 135301-135315 (2025)","raw_type":"article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/495133","is_oa":true,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/495133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3591739","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3591739","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2760476066","https://openalex.org/W2923014074","https://openalex.org/W2963532001","https://openalex.org/W2963678029","https://openalex.org/W3171472837","https://openalex.org/W3174828871","https://openalex.org/W3185341429","https://openalex.org/W3201915713","https://openalex.org/W4309773749","https://openalex.org/W4379598302","https://openalex.org/W4381930847","https://openalex.org/W4386322180","https://openalex.org/W4386867830","https://openalex.org/W4389524317","https://openalex.org/W4390561469","https://openalex.org/W4392366638","https://openalex.org/W4392384659","https://openalex.org/W4392488972","https://openalex.org/W4398183782","https://openalex.org/W4399203757","https://openalex.org/W4399203760","https://openalex.org/W4399380754","https://openalex.org/W4401719686","https://openalex.org/W4401720461","https://openalex.org/W4402683749","https://openalex.org/W4404781101","https://openalex.org/W4406085118","https://openalex.org/W4409357579","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W6782942446","https://openalex.org/W6796581206","https://openalex.org/W6843180136","https://openalex.org/W6850260469","https://openalex.org/W6850820320","https://openalex.org/W6851775633","https://openalex.org/W6857907911","https://openalex.org/W6858028522","https://openalex.org/W6859894131","https://openalex.org/W6862005606","https://openalex.org/W6867830879","https://openalex.org/W6872193714","https://openalex.org/W6880881749"],"related_works":["https://openalex.org/W4390306690","https://openalex.org/W1969209172","https://openalex.org/W4385572141","https://openalex.org/W2377297411","https://openalex.org/W4281997472","https://openalex.org/W3148217948","https://openalex.org/W3046366884","https://openalex.org/W2375788636","https://openalex.org/W2358561207","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Training":[0],"small":[1,76,106,157,189],"language":[2,36,61,77,107,158,190],"models":[3,37,62,78,191],"for":[4,79,187],"specific":[5],"tasks":[6],"often":[7],"encounters":[8],"a":[9,69,93,123,197],"significant":[10],"challenge:":[11],"the":[12,57,119,133,155,182],"limited":[13],"availability":[14],"of":[15,59,71,136,184],"high-quality":[16],"labeled":[17,85],"data,":[18,33],"which":[19],"can":[20],"restrict":[21],"model":[22,108,159],"performance.":[23],"This":[24,116],"constraint":[25],"is":[26,68],"especially":[27],"critical":[28],"in":[29,63,113],"organizations":[30],"handling":[31],"sensitive":[32],"where":[34],"large":[35,60],"cannot":[38],"be":[39],"readily":[40],"deployed":[41],"due":[42],"to":[43,74,165,192,200,205],"privacy":[44],"concerns,":[45],"high":[46],"costs,":[47],"and":[48,111,142,147,162],"dependency":[49],"on":[50,122,132,175],"external":[51],"providers.":[52],"While":[53],"existing":[54],"research":[55],"demonstrates":[56],"effectiveness":[58],"automating":[64],"text-based":[65],"tasks,":[66,195],"there":[67],"lack":[70],"methods":[72],"tailored":[73],"fine-tuning":[75,95,109,186],"secure,":[80],"domain-specific":[81],"applications":[82,204],"with":[83,127],"minimal":[84],"data.":[86],"To":[87],"address":[88],"this":[89],"gap,":[90],"we":[91],"introduce":[92],"data-centric":[94,185],"method":[96,121],"that":[97,154],"systematically":[98],"enhances":[99],"training":[100],"data":[101],"through":[102],"prompt":[103],"engineering,":[104],"making":[105],"feasible":[110],"effective":[112],"data-constrained":[114],"environments.":[115],"study":[117],"evaluates":[118],"proposed":[120],"real-world":[124,206],"use":[125,207],"case":[126],"an":[128],"industry":[129],"partner,":[130],"focusing":[131],"automatic":[134],"extraction":[135],"technical":[137],"requirements":[138],"from":[139],"full-text":[140],"documents":[141],"using":[143],"both":[144],"quantitative":[145],"metrics":[146],"qualitative":[148],"expert":[149],"assessments.":[150],"Our":[151],"findings":[152],"reveal":[153],"fine-tuned":[156],"achieves":[160],"accuracy":[161],"consistency":[163],"comparable":[164],"human":[166],"service":[167],"providers,":[168],"while":[169],"outperforming":[170],"baseline":[171],"models,":[172],"including":[173],"GPT-4-turbo,":[174],"key":[176],"evaluation":[177],"metrics.":[178],"These":[179],"results":[180],"underscore":[181],"potential":[183],"adapting":[188],"high-stakes,":[193],"privacy-sensitive":[194],"offering":[196],"scalable":[198],"alternative":[199],"LLMs":[201],"enabling":[202],"their":[203],"cases.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}