{"id":"https://openalex.org/W4410660770","doi":"https://doi.org/10.1109/access.2025.3573030","title":"The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats","display_name":"The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410660770","doi":"https://doi.org/10.1109/access.2025.3573030"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3573030","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3573030","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2025.3573030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115935895","display_name":"William Brach","orcid":"https://orcid.org/0009-0002-0321-0321"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"William Brach","raw_affiliation_strings":["Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","Faculty of Informatics and Information Technologies, Slovak University of Technology, Ilkovicova 2, Bratislava, Slovakia"],"raw_orcid":"https://orcid.org/0009-0002-0321-0321","affiliations":[{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]},{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Ilkovicova 2, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087743833","display_name":"Kristi\u00e1n Ko\u0161\u0165\u00e1l","orcid":"https://orcid.org/0000-0003-0679-4588"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Kristi\u00e1n Ko\u0161\u0165\u00e1l","raw_affiliation_strings":["Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","Faculty of Informatics and Information Technologies, Slovak University of Technology, Ilkovicova 2, Bratislava, Slovakia"],"raw_orcid":"https://orcid.org/0000-0003-0679-4588","affiliations":[{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]},{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Ilkovicova 2, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088100575","display_name":"Michal Ries","orcid":"https://orcid.org/0000-0002-9233-7123"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Michal Ries","raw_affiliation_strings":["Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","Faculty of Informatics and Information Technologies, Slovak University of Technology, Ilkovicova 2, Bratislava, Slovakia"],"raw_orcid":"https://orcid.org/0000-0002-9233-7123","affiliations":[{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]},{"raw_affiliation_string":"Faculty of Informatics and Information Technologies, Slovak University of Technology, Ilkovicova 2, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115935895"],"corresponding_institution_ids":["https://openalex.org/I110757952"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":10.388,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97826776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"91808","last_page":"91825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8389999866485596,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8389999866485596,"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":0.7955446243286133},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6064032912254333},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.42505979537963867},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4033091068267822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3813523054122925},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34139078855514526},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14144697785377502},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.07357031106948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955446243286133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6064032912254333},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.42505979537963867},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4033091068267822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813523054122925},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34139078855514526},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14144697785377502},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.07357031106948853}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3573030","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3573030","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:27a889d7fda4497aba9da2fb7409d60c","is_oa":true,"landing_page_url":"https://doaj.org/article/27a889d7fda4497aba9da2fb7409d60c","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 91808-91825 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3573030","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3573030","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1555851617","https://openalex.org/W2069726734","https://openalex.org/W2080213370","https://openalex.org/W2606974598","https://openalex.org/W2798685342","https://openalex.org/W3035507081","https://openalex.org/W3116194881","https://openalex.org/W3160638507","https://openalex.org/W3173777717","https://openalex.org/W3185341429","https://openalex.org/W4221143046","https://openalex.org/W4389520779","https://openalex.org/W4391136507","https://openalex.org/W4399729074","https://openalex.org/W4401414070","https://openalex.org/W4402727764","https://openalex.org/W4402951226","https://openalex.org/W4404365259","https://openalex.org/W4404782958","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6800751262","https://openalex.org/W6810162553","https://openalex.org/W6852496805","https://openalex.org/W6853456889","https://openalex.org/W6854874810","https://openalex.org/W6856643857","https://openalex.org/W6869227612","https://openalex.org/W6877031727","https://openalex.org/W6910521177"],"related_works":["https://openalex.org/W3203889067","https://openalex.org/W3184725726","https://openalex.org/W2378793138","https://openalex.org/W2759357633","https://openalex.org/W2591076968","https://openalex.org/W2761062406","https://openalex.org/W4241649480","https://openalex.org/W2908367543","https://openalex.org/W2486684331","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"exponential":[1],"growth":[2],"of":[3,78],"unstructured":[4,35,67,132,188],"text":[5,36,69,133],"data":[6,13,50,169],"presents":[7],"a":[8,45],"fundamental":[9],"challenge":[10],"in":[11,27,151],"modern":[12],"management":[14],"and":[15,84,186,195],"information":[16],"retrieval.":[17],"While":[18],"Large":[19],"Language":[20],"Models":[21],"(LLMs)":[22],"have":[23],"shown":[24],"remarkable":[25],"capabilities":[26],"natural":[28],"language":[29],"processing,":[30],"their":[31],"potential":[32,150],"to":[33,65,177,200],"transform":[34,130],"into":[37,70,134],"standardized,":[38],"structured":[39,72,135,168],"formats":[40,136],"remains":[41],"largely":[42],"unexplored":[43],"-":[44],"capability":[46],"that":[47,92,109,126],"could":[48],"revolutionize":[49],"processing":[51],"workflows":[52],"across":[53,171],"industries.":[54],"This":[55],"study":[56],"breaks":[57],"new":[58,164],"ground":[59],"by":[60],"systematically":[61],"evaluating":[62],"LLMs\u2019":[63],"ability":[64],"convert":[66],"recipe":[68],"the":[71,123,182,201],"Cooklang":[73],"format.":[74],"Through":[75],"comprehensive":[76],"testing":[77],"four":[79],"models":[80,153],"(GPT-4o,":[81],"GPT-4o-mini,":[82],"Llama3.3:70b,":[83],"Llama3.1:8b),":[85],"an":[86],"innovative":[87],"evaluation":[88],"approach":[89],"is":[90],"introduced":[91],"combines":[93],"traditional":[94],"metrics":[95,101],"(WER,":[96],"ROUGE-L,":[97],"TER)":[98],"with":[99,111,145],"specialized":[100],"for":[102,122,156,166],"semantic":[103],"element":[104],"identification.":[105],"Our":[106],"experiments":[107],"reveal":[108],"GPT-4o":[110],"few-shot":[112],"prompting":[113],"achieves":[114],"breakthrough":[115],"performance":[116,142],"(ROUGE-L:":[117],"0.8209,":[118],"WER:":[119],"0.3509),":[120],"demonstrating":[121],"first":[124],"time":[125],"LLMs":[127],"can":[128],"reliably":[129],"domain-specific":[131],"without":[137],"extensive":[138],"training.":[139],"Although":[140],"model":[141],"generally":[143],"scales":[144],"size,":[146],"we":[147],"uncover":[148],"surprising":[149],"smaller":[152],"like":[154],"Llama3.1:8b":[155],"optimization":[157],"through":[158],"targeted":[159],"fine-tuning.":[160],"These":[161],"findings":[162],"open":[163],"possibilities":[165],"automated":[167],"generation":[170],"various":[172],"domains,":[173],"from":[174],"medical":[175],"records":[176],"technical":[178],"documentation,":[179],"potentially":[180],"transforming":[181],"way":[183],"organizations":[184],"process":[185],"utilize":[187],"information.":[189],"For":[190],"further":[191],"information,":[192],"source":[193,202],"code,":[194],"associated":[196],"resources,":[197],"please":[198],"refer":[199],"code":[203],"repository<sup":[204],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[205],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><i>a</i></sup>.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
