{"id":"https://openalex.org/W7162779845","doi":"https://doi.org/10.48550/arxiv.2605.29168","title":"Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction","display_name":"Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162779845","doi":"https://doi.org/10.48550/arxiv.2605.29168"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29168","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29168","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.29168","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072981743","display_name":"Lorenzo Loconte","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loconte, Lorenzo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137345884","display_name":"Timothy Hospedales","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hospedales, Timothy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027858626","display_name":"Cristina Cornelio","orcid":"https://orcid.org/0000-0001-5284-6487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cornelio, Cristina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.6281999945640564,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.6281999945640564,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.13729999959468842,"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":0.10249999910593033,"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/sparql","display_name":"SPARQL","score":0.6563000082969666},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.6425999999046326},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6169000267982483},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.46219998598098755},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.435699999332428},{"id":"https://openalex.org/keywords/symbolic-execution","display_name":"Symbolic execution","score":0.4318000078201294},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43130001425743103},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41280001401901245},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.40049999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232999801635742},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.6563000082969666},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6425999999046326},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.435699999332428},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C101230327","wikidata":"https://www.wikidata.org/wiki/Q826165","display_name":"Web Ontology Language","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C234837","wikidata":"https://www.wikidata.org/wiki/Q1420493","display_name":"Conceptual graph","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C65647387","wikidata":"https://www.wikidata.org/wiki/Q1781706","display_name":"Conjunctive query","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C2778177438","wikidata":"https://www.wikidata.org/wiki/Q1437388","display_name":"Formal ontology","level":4,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29168","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29168","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.29168","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29168","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Question":[0],"answering":[1],"(QA)":[2],"is":[3],"a":[4,115,142],"core":[5],"challenge":[6],"in":[7],"AI,":[8],"particularly":[9],"for":[10,63,97,118,174],"complex":[11,69],"queries":[12],"requiring":[13],"multi-hop":[14],"reasoning":[15],"across":[16],"documents,":[17],"or":[18,23],"symbolic":[19,64,74,175],"operations":[20,65],"like":[21],"aggregation":[22],"exhaustive":[24],"listing.":[25],"Retrieval-augmented":[26],"generation":[27],"has":[28],"become":[29],"the":[30,60,168,179],"dominant":[31],"approach":[32],"to":[33,47,67,141],"QA,":[34],"with":[35],"recent":[36],"graph-based":[37,55,75],"variants":[38],"addressing":[39],"part":[40],"of":[41,127,135,181],"these":[42,92],"issues":[43],"by":[44,177],"organizing":[45],"knowledge":[46,79],"better":[48],"support":[49],"compositional":[50],"questions.":[51],"However,":[52],"most":[53],"textual":[54],"RAG":[56],"methods":[57],"still":[58],"lack":[59],"structure":[61],"needed":[62],"useful":[66],"answer":[68],"questions":[70],"reliably.":[71],"This":[72],"motivates":[73],"approaches,":[76],"which":[77,100],"extract":[78],"graphs":[80],"(KGs)":[81],"whose":[82],"relations":[83],"are":[84,171],"logic":[85],"predicates":[86],"that":[87,167],"enable":[88],"SQL-like":[89],"querying.":[90],"Yet":[91],"pipelines":[93],"typically":[94],"use":[95],"LLMs":[96],"KG":[98,120,157],"extraction,":[99,124],"can":[101],"introduce":[102],"consistency":[103,158],"issues,":[104],"where":[105],"extracted":[106,169],"facts":[107],"may":[108],"violate":[109],"commonsense":[110],"ontology":[111,136],"constraints.":[112],"We":[113],"propose":[114],"neuro-symbolic":[116],"framework":[117],"ontology-grounded":[119],"construction":[121],"combining":[122],"open-domain":[123],"embedding-based":[125],"canonicalization":[126],"types":[128],"and":[129,131,159],"predicates,":[130],"targeted":[132],"LLM-based":[133],"correction":[134],"violations.":[137],"By":[138],"deferring":[139],"corrections":[140],"post-extraction":[143],"stage,":[144],"our":[145],"method":[146],"avoids":[147],"repeated":[148],"LLM":[149],"calls,":[150],"substantially":[151],"reducing":[152],"token":[153],"usage":[154],"while":[155],"improving":[156],"preserving":[160],"downstream":[161],"QA":[162],"quality.":[163],"Finally,":[164],"we":[165],"show":[166],"KGs":[170],"well":[172],"suited":[173],"querying":[176],"measuring":[178],"occurrence":[180],"SPARQL":[182],"graph":[183],"patterns.":[184]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}