{"id":"https://openalex.org/W4392120636","doi":"https://doi.org/10.48550/arxiv.2402.14273","title":"Can Language Models Act as Knowledge Bases at Scale?","display_name":"Can Language Models Act as Knowledge Bases at Scale?","publication_year":2024,"publication_date":"2024-02-22","ids":{"openalex":"https://openalex.org/W4392120636","doi":"https://doi.org/10.48550/arxiv.2402.14273"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.14273","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.14273","pdf_url":"https://arxiv.org/pdf/2402.14273","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.14273","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025543397","display_name":"Qiyuan He","orcid":"https://orcid.org/0000-0001-9083-8285","observed_orcids":["https://orcid.org/0000-0001-9083-8285","https://orcid.org/0009-0006-6258-8956"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"He, Qiyuan","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101621485","display_name":"Yizhong Wang","orcid":"https://orcid.org/0000-0002-9760-3910","observed_orcids":["https://orcid.org/0000-0002-9760-3910"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Yizhong","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078565848","display_name":"Wenya Wang","orcid":"https://orcid.org/0000-0001-5612-7818","observed_orcids":["https://orcid.org/0000-0001-5612-7818","https://orcid.org/0000-0002-4189-6929"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wang, Wenya","raw_affiliation_strings":["Nanyang Technological University","Research Repository ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Research Repository ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":24,"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":0.9897000193595886,"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":0.9897000193595886,"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":0.003599999938160181,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0024999999441206455,"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/large-language-models","display_name":"large language models","score":0.9710000157356262},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"knowledge base","score":0.9829999804496765},{"id":"https://openalex.org/keywords/knowledge-memorization","display_name":"knowledge memorization","score":0.7789999842643738},{"id":"https://openalex.org/keywords/knowledge-retrieval","display_name":"knowledge retrieval","score":0.7480000257492065},{"id":"https://openalex.org/keywords/knowledge-based-reasoning","display_name":"knowledge reasoning","score":0.609000027179718},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.6150000095367432},{"id":"https://openalex.org/keywords/wikidata","display_name":"Wikidata","score":0.6439999938011169},{"id":"https://openalex.org/keywords/factual-knowledge","display_name":"factual knowledge","score":0.6819999814033508}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5893175601959229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48660337924957275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3265383839607239},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12455585598945618},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0757807195186615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.14273","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.14273","pdf_url":"https://arxiv.org/pdf/2402.14273","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.14273","doi":"https://doi.org/10.48550/arxiv.2402.14273","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.14273","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.14273","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.14273","pdf_url":"https://arxiv.org/pdf/2402.14273","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392120636.pdf","grobid_xml":"https://content.openalex.org/works/W4392120636.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2177410802","https://openalex.org/W2908510526","https://openalex.org/W3039578880","https://openalex.org/W4221159672","https://openalex.org/W4223974161","https://openalex.org/W4293060592","https://openalex.org/W4388092435","https://openalex.org/W4389713789","https://openalex.org/W4390572883","https://openalex.org/W6928808459","https://openalex.org/W7133245087"],"related_works":["https://openalex.org/W4386148138","https://openalex.org/W3079786700","https://openalex.org/W4412405947","https://openalex.org/W4399790320","https://openalex.org/W7104838588","https://openalex.org/W4404792828","https://openalex.org/W4223974161","https://openalex.org/W4386302414","https://openalex.org/W4312091849","https://openalex.org/W4386235866"],"abstract_inverted_index":{"Large":[0],"language":[1,113],"models":[2,24],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"proficiency":[7],"in":[8,25,92,97,109,143],"understanding":[9],"and":[10,27,56,138],"generating":[11],"responses":[12],"to":[13,65,80,111,118,149],"complex":[14],"queries":[15],"through":[16,122],"large-scale":[17,30,99,133],"pre-training.":[18],"However,":[19],"the":[20,82,85,94,98,102,106,116],"efficacy":[21],"of":[22,87,104,136],"these":[23],"memorizing":[26,93],"reasoning":[28,145],"among":[29],"structured":[31],"knowledge,":[32],"especially":[33],"world":[34],"knowledge":[35,59,67,96,108,121],"that":[36,127],"explicitly":[37],"covers":[38],"abundant":[39],"factual":[40],"information":[41],"remains":[42],"questionable.":[43],"Addressing":[44],"this":[45],"gap,":[46],"our":[47],"research":[48],"investigates":[49],"whether":[50],"LLMs":[51,88,129],"can":[52],"effectively":[53],"store,":[54],"recall,":[55],"reason":[57],"with":[58,89,140],"on":[60,76],"a":[61],"large":[62],"scale":[63],"comparable":[64],"latest":[66],"bases":[68],"(KBs)":[69],"such":[70],"as":[71,132],"Wikidata.":[72],"Specifically,":[73],"we":[74],"focus":[75],"three":[77],"crucial":[78],"aspects":[79],"study":[81],"viability:":[83],"(1)":[84],"efficiency":[86],"different":[90],"sizes":[91],"exact":[95],"KB;":[100],"(2)":[101],"flexibility":[103],"recalling":[105],"memorized":[107],"response":[110],"natural":[112],"queries;":[114],"(3)":[115],"capability":[117],"infer":[119],"new":[120],"reasoning.":[123],"Our":[124],"findings":[125],"indicate":[126],"while":[128],"hold":[130],"promise":[131],"KBs":[134],"capable":[135],"retrieving":[137],"responding":[139],"flexibility,":[141],"enhancements":[142],"their":[144,152],"capabilities":[146],"are":[147],"necessary":[148],"fully":[150],"realize":[151],"potential.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-02-24T00:00:00"}