{"id":"https://openalex.org/W7117988664","doi":"https://doi.org/10.1109/enc68268.2025.11311861","title":"Scalable Construction of a Lung Cancer Knowledge Base: Profiling Semantic Reasoning in LLMs","display_name":"Scalable Construction of a Lung Cancer Knowledge Base: Profiling Semantic Reasoning in LLMs","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7117988664","doi":"https://doi.org/10.1109/enc68268.2025.11311861"},"language":null,"primary_location":{"id":"doi:10.1109/enc68268.2025.11311861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/enc68268.2025.11311861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Mexican International Conference on Computer Science (ENC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.02604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120190110","display_name":"Cesar Felipe Mart\u00ednez Cisneros","orcid":null},"institutions":[{"id":"https://openalex.org/I179297788","display_name":"Technological University of the Mixteca","ror":"https://ror.org/003eaqr04","country_code":"MX","type":"education","lineage":["https://openalex.org/I179297788"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Cesar Felipe Mart\u00ednez Cisneros","raw_affiliation_strings":["Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico"],"affiliations":[{"raw_affiliation_string":"Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico","institution_ids":["https://openalex.org/I179297788"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121800322","display_name":"Jes\u00fas Ulises Quiroz Bautista","orcid":null},"institutions":[{"id":"https://openalex.org/I179297788","display_name":"Technological University of the Mixteca","ror":"https://ror.org/003eaqr04","country_code":"MX","type":"education","lineage":["https://openalex.org/I179297788"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Ulises Quiroz Bautista","raw_affiliation_strings":["Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico"],"affiliations":[{"raw_affiliation_string":"Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico","institution_ids":["https://openalex.org/I179297788"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116542470","display_name":"Claudia Anah\u00ed Guzm\u00e1n Solano","orcid":null},"institutions":[{"id":"https://openalex.org/I179297788","display_name":"Technological University of the Mixteca","ror":"https://ror.org/003eaqr04","country_code":"MX","type":"education","lineage":["https://openalex.org/I179297788"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Claudia Anah\u00ed Guzm\u00e1n Solano","raw_affiliation_strings":["Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico"],"affiliations":[{"raw_affiliation_string":"Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico","institution_ids":["https://openalex.org/I179297788"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120190109","display_name":"Bogdan Kaleb Garc\u00eda Rivera","orcid":null},"institutions":[{"id":"https://openalex.org/I179297788","display_name":"Technological University of the Mixteca","ror":"https://ror.org/003eaqr04","country_code":"MX","type":"education","lineage":["https://openalex.org/I179297788"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Bogdan Kaleb Garc\u00eda Rivera","raw_affiliation_strings":["Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico"],"affiliations":[{"raw_affiliation_string":"Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico","institution_ids":["https://openalex.org/I179297788"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067705573","display_name":"Iv\u00e1n Garc\u00eda Pacheco","orcid":null},"institutions":[{"id":"https://openalex.org/I179297788","display_name":"Technological University of the Mixteca","ror":"https://ror.org/003eaqr04","country_code":"MX","type":"education","lineage":["https://openalex.org/I179297788"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Iv\u00e1n Garc\u00eda Pacheco","raw_affiliation_strings":["Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico"],"affiliations":[{"raw_affiliation_string":"Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico","institution_ids":["https://openalex.org/I179297788"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121827655","display_name":"Yalbi Itzel Balderas Mart\u00ednez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102695","display_name":"Instituto Nacional de Enfermedades Respiratorias","ror":"https://ror.org/017fh2655","country_code":"MX","type":"facility","lineage":["https://openalex.org/I4210095685","https://openalex.org/I4210102695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Yalbi Itzel Balderas Mart\u00ednez","raw_affiliation_strings":["Instituto Nacional de Enfermedades Respiratorias (INER) Ismael Cos&#x00ED;o Villegas,Ciudad de M&#x00E9;xico,M&#x00E9;xico"],"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Enfermedades Respiratorias (INER) Ismael Cos&#x00ED;o Villegas,Ciudad de M&#x00E9;xico,M&#x00E9;xico","institution_ids":["https://openalex.org/I4210102695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017923726","display_name":"Kolawole John Adebayo","orcid":"https://orcid.org/0000-0001-7126-7026"},"institutions":[{"id":"https://openalex.org/I157286207","display_name":"National University of Ireland, Maynooth","ror":"https://ror.org/048nfjm95","country_code":"IE","type":"education","lineage":["https://openalex.org/I157286207"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kolawole John Adebayo","raw_affiliation_strings":["Maynooth University,Maynooth,Ireland"],"affiliations":[{"raw_affiliation_string":"Maynooth University,Maynooth,Ireland","institution_ids":["https://openalex.org/I157286207"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121821301","display_name":"Ignacio Arroyo Fern\u00e1ndez","orcid":null},"institutions":[{"id":"https://openalex.org/I179297788","display_name":"Technological University of the Mixteca","ror":"https://ror.org/003eaqr04","country_code":"MX","type":"education","lineage":["https://openalex.org/I179297788"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ignacio Arroyo Fern\u00e1ndez","raw_affiliation_strings":["Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico"],"affiliations":[{"raw_affiliation_string":"Universidad Tecnol&#x00F3;gica de la Mixteca, Huajuapan de Le&#x00F3;n,Oaxaca,M&#x00E9;xico","institution_ids":["https://openalex.org/I179297788"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5120190110"],"corresponding_institution_ids":["https://openalex.org/I179297788"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85260945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7736999988555908,"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":0.7736999988555908,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.05820000171661377,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.02850000001490116,"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/interpretability","display_name":"Interpretability","score":0.7878000140190125},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.558899998664856},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5234000086784363},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5146999955177307},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.46709999442100525},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3709000051021576},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3594000041484833},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7878000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874000072479248},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080000162124634},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.445499986410141},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.28679999709129333},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C56289545","wikidata":"https://www.wikidata.org/wiki/Q6423376","display_name":"Knowledge integration","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/enc68268.2025.11311861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/enc68268.2025.11311861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Mexican International Conference on Computer Science (ENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.02604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.02604","pdf_url":"https://arxiv.org/pdf/2601.02604","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.02604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.02604","pdf_url":"https://arxiv.org/pdf/2601.02604","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.40545669198036194,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2081580037","https://openalex.org/W2250225327","https://openalex.org/W2587223734","https://openalex.org/W2891678595","https://openalex.org/W2958285100","https://openalex.org/W2966351171","https://openalex.org/W3003265726","https://openalex.org/W3004611733","https://openalex.org/W3093988619","https://openalex.org/W3199885074","https://openalex.org/W4226229083","https://openalex.org/W4378470138","https://openalex.org/W4382246105","https://openalex.org/W4385245566","https://openalex.org/W4387645476","https://openalex.org/W4388144374","https://openalex.org/W4411451451"],"related_works":[],"abstract_inverted_index":{"The":[0,68,111],"integration":[1],"of":[2,28,153],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"into":[7],"biomedical":[8,109,162],"research":[9],"offers":[10],"new":[11],"opportunities":[12],"for":[13,41,48,56,122,160],"domain-specific":[14],"reasoning":[15],"and":[16,35,97,119,141,147],"knowledge":[17,44,61],"representation.":[18],"However,":[19],"their":[20],"performance":[21,146],"depends":[22],"heavily":[23],"on":[24,130],"the":[25,76,151],"semantic":[26,148],"quality":[27],"training":[29],"data.":[30],"In":[31],"oncology,":[32],"where":[33],"precision":[34],"interpretability":[36],"are":[37,46],"vital,":[38],"scalable":[39],"methods":[40],"constructing":[42],"structured":[43],"bases":[45],"essential":[47],"effective":[49],"fine-tuning.":[50],"This":[51],"study":[52],"presents":[53],"a":[54,58,116],"pipeline":[55],"developing":[57],"lung":[59],"cancer":[60],"base":[62],"using":[63,94],"Open":[64],"Information":[65],"Extraction":[66],"(OpenIE).":[67],"process":[69],"includes:":[70],"(1)":[71],"identifying":[72],"medical":[73],"concepts":[74],"with":[75,84,102,139],"MeSH":[77],"thesaurus;":[78],"(2)":[79],"filtering":[80],"open-access":[81],"PubMed":[82],"literature":[83],"permissive":[85],"licenses":[86],"(CC0);":[87],"(3)":[88],"extracting":[89],"(subject,":[90],"relation,":[91],"object)":[92],"triplets":[93],"OpenIE":[95],"method;":[96],"(4)":[98],"enriching":[99],"triplet":[100,113],"sets":[101,114],"Named":[103],"Entity":[104],"Recognition":[105],"(NER)":[106],"to":[107],"ensure":[108],"relevance.":[110],"resulting":[112],"provide":[115],"domain-specific,":[117],"large-scale,":[118],"noise-aware":[120],"resource":[121],"fine-tuning":[123],"LLMs.":[124],"We":[125],"evaluated":[126],"T5":[127],"models":[128],"fine-tuned":[129],"this":[131],"dataset":[132],"through":[133],"Supervised":[134],"Semantic":[135],"Fine-Tuning.":[136],"Comparative":[137],"assessments":[138],"ROUGE":[140],"BERTScore":[142],"show":[143],"significantly":[144],"improved":[145],"coherence,":[149],"demonstrating":[150],"potential":[152],"OpenIE-derived":[154],"resources":[155],"as":[156],"scalable,":[157],"low-cost":[158],"solutions":[159],"enhancing":[161],"NLP.":[163]},"counts_by_year":[],"updated_date":"2026-01-03T23:08:47.215875","created_date":"2026-01-02T00:00:00"}
