{"id":"https://openalex.org/W7138153002","doi":"https://doi.org/10.1609/aaai.v40i23.38969","title":"VSPO: Validating Semantic Pitfalls in Ontology via LLM-Based CQ Generation","display_name":"VSPO: Validating Semantic Pitfalls in Ontology via LLM-Based CQ Generation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138153002","doi":"https://doi.org/10.1609/aaai.v40i23.38969"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i23.38969","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i23.38969","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i23.38969","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052833392","display_name":"Hyojun Choi","orcid":"https://orcid.org/0000-0002-2427-0107"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hyojun Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733355","display_name":"Seokju Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seokju Hwang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044514062","display_name":"Kyong-Ho Lee","orcid":"https://orcid.org/0000-0002-1581-917X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyong-Ho Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052833392"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33173996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"23","first_page":"18977","last_page":"18984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.8062999844551086,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8062999844551086,"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/T10028","display_name":"Topic Modeling","score":0.05559999868273735,"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":0.041999999433755875,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7386000156402588},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5612999796867371},{"id":"https://openalex.org/keywords/axiom","display_name":"Axiom","score":0.5411999821662903},{"id":"https://openalex.org/keywords/semantic-heterogeneity","display_name":"Semantic heterogeneity","score":0.4456000030040741},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44110000133514404},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4050000011920929},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3910999894142151},{"id":"https://openalex.org/keywords/ontology-alignment","display_name":"Ontology alignment","score":0.3605000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163999915122986},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7386000156402588},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4814000129699707},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.4456000030040741},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4284999966621399},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C98893333","wikidata":"https://www.wikidata.org/wiki/Q4339878","display_name":"Ontology alignment","level":4,"score":0.3605000078678131},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C110903229","wikidata":"https://www.wikidata.org/wiki/Q7449064","display_name":"Semantic integration","level":4,"score":0.32690000534057617},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2778820784","wikidata":"https://www.wikidata.org/wiki/Q1027508","display_name":"Ontology engineering","level":4,"score":0.27720001339912415},{"id":"https://openalex.org/C78726541","wikidata":"https://www.wikidata.org/wiki/Q3882785","display_name":"Upper ontology","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i23.38969","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i23.38969","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i23.38969","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i23.38969","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4905860722064972}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Competency":[0],"Questions":[1],"(CQs)":[2],"play":[3],"a":[4,77,163],"crucial":[5],"role":[6],"in":[7,86,192,237],"validating":[8],"ontology":[9,22,125],"design.":[10],"While":[11],"manually":[12],"crafting":[13],"CQs":[14,46,144,160,194,205],"can":[15,161],"be":[16,69],"highly":[17],"time-consuming":[18],"and":[19,80,102,115,117,123,154,186,218],"costly":[20],"for":[21,89,195],"engineers,":[23],"recent":[24],"studies":[25],"have":[26,42],"explored":[27],"the":[28,96,121,124,151,155,222,229],"use":[29,106],"of":[30,82,113,166,203,224],"large":[31],"language":[32,111],"models":[33],"(LLMs)":[34],"to":[35,51,57,94,108,142,170,232],"automate":[36],"this":[37,227],"process.":[38],"However,":[39],"prior":[40],"approaches":[41],"largely":[43],"evaluated":[44],"generated":[45],"based":[47],"on":[48],"their":[49],"similarity":[50],"existing":[52,171],"datasets,":[53],"which":[54],"often":[55],"fail":[56],"verify":[58,95],"semantic":[59,97,148,214,234],"pitfalls":[60,67],"such":[61,66],"as":[62],"\u201cMisusing":[63],"allValuesFrom\u201d.":[64],"Since":[65],"cannot":[68],"reliably":[70],"detected":[71],"through":[72],"rule-based":[73],"methods,":[74],"we":[75,105],"propose":[76],"novel":[78],"dataset":[79],"model":[81,176],"Validating":[83],"Semantic":[84],"Pitfalls":[85],"Ontology":[87],"(VSPO)":[88],"CQ":[90,238],"generation":[91,202,239],"specifically":[92],"designed":[93],"pitfalls.":[98],"To":[99,221],"simulate":[100],"missing":[101],"misused":[103],"axioms,":[104],"LLM":[107],"generate":[109,143],"natural":[110],"definitions":[112,122,153],"classes":[114],"properties":[116],"introduce":[118],"misalignments":[119],"between":[120,150,216],"by":[126],"removing":[127],"axioms":[128],"or":[129],"altering":[130],"logical":[131],"operators":[132],"(e.g.,":[133],"substituting":[134],"union":[135],"with":[136],"intersection).":[137],"We":[138],"then":[139],"fine-tune":[140],"LLaMA-3.1-8B-Instruct":[141],"that":[145],"validate":[146],"these":[147],"discrepancies":[149],"provided":[152],"corresponding":[156],"axioms.":[157],"The":[158],"resulting":[159],"detect":[162],"broader":[164],"range":[165],"modeling":[167],"errors":[168],"compared":[169],"public":[172],"datasets.":[173],"Our":[174],"fine-tuned":[175],"demonstrates":[177],"superior":[178],"performance":[179],"over":[180],"baselines,":[181],"showing":[182],"26%":[183],"higher":[184,188],"precision":[185],"28.2%":[187],"recall":[189],"than":[190],"GPT-4.1":[191],"generating":[193],"pitfall":[196,235],"validation.":[197],"This":[198],"research":[199],"enables":[200],"automatic":[201],"TBox-validating":[204],"using":[206,240],"LLMs,":[207],"significantly":[208],"reducing":[209],"manual":[210],"effort":[211],"while":[212],"improving":[213],"alignment":[215],"ontologies":[217],"expert":[219],"knowledge.":[220],"best":[223],"our":[225],"knowledge,":[226],"is":[228],"first":[230],"study":[231],"target":[233],"validation":[236],"LLMs.":[241]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}