{"id":"https://openalex.org/W4416832937","doi":"https://doi.org/10.48550/arxiv.2507.13411","title":"Aligning Knowledge Graphs and Language Models for Factual Accuracy","display_name":"Aligning Knowledge Graphs and Language Models for Factual Accuracy","publication_year":2025,"publication_date":"2025-07-17","ids":{"openalex":"https://openalex.org/W4416832937","doi":"https://doi.org/10.48550/arxiv.2507.13411"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.13411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.13411","pdf_url":"https://arxiv.org/pdf/2507.13411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.13411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120672342","display_name":"Nur A Zarin Nishat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishat, Nur A Zarin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051607028","display_name":"Andrea Coletta","orcid":"https://orcid.org/0000-0003-1401-1715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Coletta, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049287242","display_name":"Luigi Bellomarini","orcid":"https://orcid.org/0000-0001-6863-0162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bellomarini, Luigi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084774918","display_name":"Kossi Amouzouvi","orcid":"https://orcid.org/0000-0002-3614-0449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amouzouvi, Kossi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067133778","display_name":"Jens Lehmann","orcid":"https://orcid.org/0000-0001-9108-4278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lehmann, Jens","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102785999","display_name":"Sahar Vahdati","orcid":"https://orcid.org/0000-0002-7171-169X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vahdati, Sahar","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/T10028","display_name":"Topic Modeling","score":0.4489000141620636,"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":0.4489000141620636,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.336899995803833,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09749999642372131,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/embedding","display_name":"Embedding","score":0.6689000129699707},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6603000164031982},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.6208999752998352},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5306000113487244},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4537000060081482},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786300003528595},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6689000129699707},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6603000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6247000098228455},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6061000227928162},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.36660000681877136},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.3409999907016754},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.13411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.13411","pdf_url":"https://arxiv.org/pdf/2507.13411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.13411","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.13411","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:arXiv.org:2507.13411","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.13411","pdf_url":"https://arxiv.org/pdf/2507.13411","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Large":[0],"language":[1,11,50,70,85,100,141,165],"models":[2,51,101,166],"like":[3],"GPT-4,":[4],"Gemini,":[5],"and":[6,22,64,107,126,134,151,195],"Claude":[7],"have":[8],"transformed":[9],"natural":[10],"processing":[12],"(NLP)":[13],"tasks":[14],"such":[15,123],"as":[16,31,54,58,124],"question":[17],"answering,":[18],"dialogue":[19],"generation,":[20],"summarization,":[21],"so":[23],"forth;":[24],"yet":[25,80],"their":[26],"susceptibility":[27],"to":[28,40,68,83,92,131,143,178],"hallucination":[29],"stands":[30],"one":[32],"of":[33,45,99,167,201],"the":[34,69,96,140,202],"major":[35],"challenges.":[36],"Among":[37],"numerous":[38],"approaches":[39],"overcome":[41],"this":[42,73],"challenge,":[43],"integration":[44],"Knowledge":[46,118],"Graphs":[47],"(KGs)":[48],"into":[49,95],"has":[52],"emerged":[53],"a":[55,78,89,116,127,179,185,198],"promising":[56],"solution":[57],"it":[59],"provides":[60],"structured,":[61],"reliable,":[62],"domain-specific,":[63],"up-to-date":[65],"external":[66],"information":[67,109],"models.":[71],"In":[72],"paper,":[74],"we":[75,174],"introduce":[76],"ALIGNed-LLM,":[77],"simple":[79],"effective":[81],"approach":[82,157,177],"improve":[84],"models'":[86],"factuality":[87],"via":[88],"lean":[90],"strategy":[91],"infuse":[93],"KGs":[94],"latent":[97],"space":[98],"inspired":[102],"by":[103],"LLaVA":[104],"where":[105],"visual":[106],"textual":[108],"is":[110],"infused.":[111],"We":[112,154],"use":[113,182],"embeddings":[114],"from":[115,184],"pre-trained":[117],"Graph":[119],"Embedding":[120],"(KGE)":[121],"model,":[122],"TransE,":[125],"trainable":[128],"projection":[129],"layer":[130],"align":[132],"entity":[133],"text":[135],"embeddings.":[136],"This":[137],"alignment":[138],"enables":[139],"model":[142],"distinguish":[144],"between":[145],"similar":[146],"entities":[147],"improving":[148],"factual":[149],"grounding":[150],"reducing":[152],"hallucination.":[153],"tested":[155],"our":[156,176],"on":[158],"three":[159],"popular":[160],"questions-answering":[161],"benchmark":[162],"datasets":[163],"alongside":[164],"varying":[168],"sizes,":[169],"showing":[170],"significant":[171],"improvement.":[172],"Furthermore,":[173],"applied":[175],"real-world":[180],"financial":[181],"case":[183],"large":[186],"central":[187],"bank":[188],"in":[189],"Europe,":[190],"which":[191],"demands":[192],"high":[193],"accuracy":[194],"precision,":[196],"demonstrating":[197],"substantial":[199],"improvement":[200],"LLM":[203],"answers.":[204]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}