{"id":"https://openalex.org/W4412945344","doi":"https://doi.org/10.18653/v1/2025.acl-long.622","title":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering","display_name":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945344","doi":"https://doi.org/10.18653/v1/2025.acl-long.622"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.622","pdf_url":"https://aclanthology.org/2025.acl-long.622.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.622.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101399147","display_name":"Yuan Sui","orcid":"https://orcid.org/0000-0001-8559-831X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Sui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102676899","display_name":"Yufei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufei He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012515392","display_name":"Zifeng Ding","orcid":"https://orcid.org/0009-0000-9713-2701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zifeng Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065675832","display_name":"Bryan Hooi","orcid":"https://orcid.org/0000-0002-5645-1754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Hooi","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":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12685","last_page":"12701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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":0.9968000054359436,"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":0.968999981880188,"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":0.9049000144004822,"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/computer-science","display_name":"Computer science","score":0.8032978177070618},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7854233980178833},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5889763832092285},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5392765998840332},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5132560729980469},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44324949383735657},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3906572163105011},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3888247013092041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32962751388549805},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.11918884515762329},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07464221119880676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032978177070618},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7854233980178833},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5889763832092285},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5392765998840332},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5132560729980469},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44324949383735657},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3906572163105011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3888247013092041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32962751388549805},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.11918884515762329},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07464221119880676},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.622","pdf_url":"https://aclanthology.org/2025.acl-long.622.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.622","pdf_url":"https://aclanthology.org/2025.acl-long.622.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945344.pdf","grobid_xml":"https://content.openalex.org/works/W4412945344.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W4401140950"],"abstract_inverted_index":{"Recent":[0],"works":[1],"integrating":[2,176],"Knowledge":[3],"Graphs":[4],"(KGs)":[5],"have":[6],"shown":[7],"promising":[8],"improvements":[9,93],"in":[10,30,50,70,94,100,145,175],"enhancing":[11],"the":[12,98,120],"reasoning":[13,92],"capabilities":[14],"of":[15,44,107,124],"Large":[16],"Language":[17],"Models":[18],"(LLMs).However,":[19],"existing":[20],"benchmarks":[21],"primarily":[22],"focus":[23],"on":[24,33,158],"closedended":[25],"tasks,":[26],"leaving":[27],"a":[28,41,59,111,152,166],"gap":[29],"evaluating":[31],"performance":[32,118,169],"more":[34,143,167,186],"complex,":[35],"real-world":[36,72],"scenarios.This":[37],"limitation":[38],"also":[39],"hinders":[40],"thorough":[42],"assessment":[43],"KGs'":[45],"potential":[46],"to":[47,64,86,115,135,155,180],"reduce":[48],"hallucinations":[49],"LLMs.To":[51],"address":[52],"this,":[53],"we":[54,109,133],"introduce":[55],"OKGQA":[56],"1":[57],",":[58],"new":[60],"benchmark":[61,112],"specifically":[62],"designed":[63],"evaluate":[65],"LLMs":[66,142,179,185],"augmented":[67],"with":[68,178],"KGs":[69,102,125,139,177],"open-ended,":[71],"question":[73,81],"answering":[74],"settings.OKGQA":[75],"reflects":[76],"practical":[77],"complexities":[78],"through":[79],"diverse":[80],"types":[82],"and":[83,91,122,129,149,171,183],"incorporates":[84],"metrics":[85],"quantify":[87],"both":[88],"hallucination":[89],"rates":[90],"LLM+KG":[95],"models.To":[96],"consider":[97],"scenarios":[99],"which":[101],"may":[103],"contain":[104],"varying":[105],"levels":[106],"errors,":[108],"propose":[110],"variant,":[113],"OKGQA-P,":[114],"assess":[116],"model":[117],"when":[119],"semantics":[121],"structure":[123],"are":[126],"deliberately":[127],"perturbed":[128],"contaminated.In":[130],"this":[131,162],"paper,":[132],"aims":[134],"(1)":[136],"explore":[137],"whether":[138],"can":[140,164],"make":[141,184],"trustworthy":[144],"an":[146],"open-ended":[147],"setting,":[148],"(2)":[150],"conduct":[151],"comparative":[153],"analysis":[154],"shed":[156],"light":[157],"method":[159],"design.We":[160],"believe":[161],"study":[163],"facilitate":[165],"complete":[168],"comparison":[170],"encourages":[172],"continuous":[173],"improvement":[174],"mitigate":[181],"hallucination,":[182],"trustworthy.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}