{"id":"https://openalex.org/W7140103421","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.206","title":"KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge","display_name":"KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140103421","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.206"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.206","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.206","pdf_url":"https://aclanthology.org/2026.findings-eacl.206.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.206.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alex Robertson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Robertson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huizhi Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huizhi Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mahbub Gani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahbub Gani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rohit Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Srijith Rajamohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srijith Rajamohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39581809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3975","last_page":"3989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.15600000321865082,"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":0.15600000321865082,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.11379999667406082,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.061900001019239426,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.552299976348877},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.29330000281333923},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.2818000018596649},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.27970001101493835},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2653999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533999800682068},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515000224113464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2705000042915344},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.206","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.206","pdf_url":"https://aclanthology.org/2026.findings-eacl.206.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.206","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.206","pdf_url":"https://aclanthology.org/2026.findings-eacl.206.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140103421.pdf","grobid_xml":"https://content.openalex.org/works/W7140103421.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"possess":[4],"a":[5,43,60,123],"remarkable":[6],"capacity":[7],"to":[8,18,73,85,105,142],"generate":[9],"persuasive":[10],"and":[11,38,54,62,94,102,118],"intelligible":[12],"language.However,":[13],"coherence":[14],"does":[15],"not":[16],"equate":[17],"truthfulness,":[19],"as":[20],"the":[21,52,71,96,128],"responses":[22],"often":[23],"contain":[24],"subtle":[25],"hallucinations.Existing":[26],"benchmarks":[27],"are":[28],"constrained":[29],"by":[30],"static,":[31],"narrow":[32],"questions,":[33,78],"resulting":[34],"in":[35,146],"limited":[36],"coverage":[37],"misleading":[39],"evaluations.We":[40],"present":[41],"KGHaluBench,":[42],"Knowledge":[44],"Graph-based":[45],"hallucination":[46,119,147],"benchmark":[47],"that":[48,131],"assesses":[49],"LLMs":[50],"across":[51,134],"breadth":[53],"depth":[55],"of":[56,109],"their":[57],"knowledge,":[58],"providing":[59],"fairer":[61],"more":[63,124],"comprehensive":[64],"insight":[65,126],"into":[66,127],"LLM":[67],"truthfulness.Our":[68],"framework":[69],"utilises":[70],"KG":[72],"dynamically":[74],"construct":[75],"challenging,":[76],"multifaceted":[77],"whose":[79],"difficulty":[80],"is":[81,138],"then":[82],"statistically":[83],"estimated":[84],"address":[86],"popularity":[87],"bias.Our":[88],"automated":[89],"verification":[90],"pipeline":[91],"detects":[92],"abstentions":[93],"verifies":[95],"LLM's":[97],"response":[98],"at":[99],"both":[100],"conceptual":[101],"correctness":[103],"levels":[104],"identify":[106],"different":[107,135],"types":[108],"hallucinations.We":[110],"evaluate":[111],"25":[112],"frontier":[113],"models,":[114],"using":[115],"novel":[116],"accuracy":[117],"metrics.The":[120],"results":[121],"provide":[122],"interpretable":[125],"knowledge":[129],"factors":[130],"cause":[132],"hallucinations":[133],"model":[136],"sizes.KGHaluBench":[137],"publicly":[139],"available":[140],"1":[141],"support":[143],"future":[144],"developments":[145],"mitigation.":[148]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-01T00:00:00"}