{"id":"https://openalex.org/W4386566424","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.139","title":"Crawling The Internal Knowledge-Base of Language Models","display_name":"Crawling The Internal Knowledge-Base of Language Models","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386566424","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.139"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-eacl.139","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-eacl.139","pdf_url":"https://aclanthology.org/2023.findings-eacl.139.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-eacl.139.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060037698","display_name":"Roi Cohen","orcid":"https://orcid.org/0000-0002-1345-3696","observed_orcids":["https://orcid.org/0000-0002-1345-3696"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roi Cohen","raw_affiliation_strings":["Blavatnik School of Computer Science, Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blavatnik School of Computer Science, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065717258","display_name":"Mor Geva","orcid":"https://orcid.org/0000-0001-9529-6315","observed_orcids":["https://orcid.org/0000-0001-9529-6315"]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mor Geva","raw_affiliation_strings":["Allen Institute for AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045872048","display_name":"Jonathan Berant","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Jonathan Berant","raw_affiliation_strings":["Blavatnik School of Computer Science, Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blavatnik School of Computer Science, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047817959","display_name":"Amir Globerson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Amir Globerson","raw_affiliation_strings":["Blavatnik School of Computer Science, Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Blavatnik School of Computer Science, Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045872048"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":4.5956,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.96195678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1856","last_page":"1869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9804999828338623,"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":0.9804999828338623,"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":0.0035000001080334187,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0035000001080334187,"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/language-models","display_name":"language models","score":0.675000011920929},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.6320000290870667},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"knowledge extraction","score":0.6019999980926514},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.5569999814033508},{"id":"https://openalex.org/keywords/factual-knowledge","display_name":"factual knowledge","score":0.7319999933242798},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"precision and recall","score":0.7239999771118164}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8385412693023682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301191329956055},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.7495847940444946},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6107466220855713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5914117097854614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5453429222106934},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5047386884689331},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4902632534503937},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47802433371543884},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4732190668582916},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46734315156936646},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4499564468860626},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4300639033317566},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4105379581451416},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36530277132987976},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21179422736167908},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08449253439903259},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.findings-eacl.139","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-eacl.139","pdf_url":"https://aclanthology.org/2023.findings-eacl.139.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.12810","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.12810","pdf_url":"https://arxiv.org/pdf/2301.12810","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.2301.12810","doi":"https://doi.org/10.48550/arxiv.2301.12810","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2301.12810","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":"doi:10.18653/v1/2023.findings-eacl.139","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.139","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-eacl.139","pdf_url":"https://aclanthology.org/2023.findings-eacl.139.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386566424.pdf","grobid_xml":"https://content.openalex.org/works/W4386566424.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2038721957","https://openalex.org/W2167187514","https://openalex.org/W2251913848","https://openalex.org/W2561529111","https://openalex.org/W2963318887","https://openalex.org/W2981852735","https://openalex.org/W3012209028","https://openalex.org/W3030163527","https://openalex.org/W3118781290","https://openalex.org/W3199958362","https://openalex.org/W3206959854","https://openalex.org/W4221143046","https://openalex.org/W4223974161","https://openalex.org/W4224308101","https://openalex.org/W4281748205","https://openalex.org/W4285298351","https://openalex.org/W4285429195","https://openalex.org/W4293060592","https://openalex.org/W4298187912","https://openalex.org/W4303441863","https://openalex.org/W4385570599","https://openalex.org/W7133208784"],"related_works":["https://openalex.org/W2951048068","https://openalex.org/W3093871960","https://openalex.org/W4318351203","https://openalex.org/W4387356334","https://openalex.org/W4407268166","https://openalex.org/W4402671536","https://openalex.org/W2476140796","https://openalex.org/W3034085606","https://openalex.org/W7140138109","https://openalex.org/W7166015818"],"abstract_inverted_index":{"Language":[0],"models":[1,28],"are":[2,122],"trained":[3],"on":[4,31,135],"large":[5],"volumes":[6],"of":[7,20,47,72,87,129,141,157],"text,":[8],"and":[9,34,124,144],"as":[10],"a":[11,17,60,70,75,80,88,92,97,154],"result":[12],"their":[13],"parameters":[14],"might":[15],"contain":[16],"significant":[18],"body":[19,46],"factual":[21],"knowledge.Any":[22],"downstream":[23],"task":[24],"performed":[25],"by":[26,68],"these":[27,32],"implicitly":[29],"builds":[30],"facts,":[33],"thus":[35],"it":[36,146],"is":[37,54,103],"highly":[38],"desirable":[39],"to":[40,64],"have":[41],"means":[42],"for":[43,58,82,114],"representing":[44],"this":[45,66],"knowledge":[48],"in":[49],"an":[50],"interpretable":[51],"way.However,":[52],"there":[53],"currently":[55],"no":[56,119],"mechanism":[57],"such":[59],"representation.Here,":[61],"we":[62,95],"propose":[63],"address":[65],"goal":[67],"extracting":[69],"knowledgegraph":[71],"facts":[73,121,130,158],"from":[74,139],"given":[76,91],"language":[77,89],"model.We":[78],"describe":[79],"procedure":[81,102],"\"crawling\"":[83],"the":[84,127],"internal":[85],"knowledge-base":[86],"model.Specifically,":[90],"seed":[93,142],"entity,":[94],"expand":[96],"knowledge-graph":[98],"around":[99],"it.The":[100],"crawling":[101],"decomposed":[104],"into":[105],"sub-tasks,":[106],"realized":[107],"through":[108],"specially":[109],"designed":[110],"prompts":[111],"that":[112,118],"control":[113],"both":[115],"precision":[116,149],"(i.e.,":[117,126],"wrong":[120],"generated)":[123],"recall":[125],"number":[128,156],"generated).We":[131],"evaluate":[132],"our":[133],"approach":[134],"graphs":[136,150],"crawled":[137],"starting":[138],"dozens":[140],"entities,":[143],"show":[145],"yields":[147],"high":[148],"(82-92%),":[151],"while":[152],"emitting":[153],"reasonable":[155],"per":[159],"entity.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-09-10T00:00:00"}