{"id":"https://openalex.org/W4412877088","doi":"https://doi.org/10.1145/3711896.3737444","title":"WikiRAG: Revisiting Wikidata KGC Datasets with Community Updates and Retrieval-Augmented Generation","display_name":"WikiRAG: Revisiting Wikidata KGC Datasets with Community Updates and Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877088","doi":"https://doi.org/10.1145/3711896.3737444"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737444","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737444","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737444","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088762737","display_name":"Djellel Difallah","orcid":"https://orcid.org/0000-0002-7513-6047"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Djellel Difallah","raw_affiliation_strings":["New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088762737"],"corresponding_institution_ids":["https://openalex.org/I120250893"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10525794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5391","last_page":"5401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.8034443855285645},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.635929524898529},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4113748073577881},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34212321043014526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034443855285645},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.635929524898529},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4113748073577881},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34212321043014526}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737444","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737444","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737444","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737444","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737444","source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877088.pdf","grobid_xml":"https://content.openalex.org/works/W4412877088.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2127795553","https://openalex.org/W3003265726","https://openalex.org/W3044410371","https://openalex.org/W3091993229","https://openalex.org/W3120491054","https://openalex.org/W3130909864","https://openalex.org/W3151929433","https://openalex.org/W3155001903","https://openalex.org/W4386443326","https://openalex.org/W6788056113"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Link":[0],"prediction":[1,236],"is":[2],"an":[3,228],"important":[4],"task":[5,218],"for":[6,74,120,175,244],"knowledge":[7,56,75,249],"graph":[8,142,187],"completion":[9,76,250],"and":[10,12,26,48,77,82,90,116,144,170,260],"curation,":[11],"it":[13,108],"has":[14],"received":[15],"significant":[16],"attention":[17],"from":[18,80,134],"the":[19,39,49,97,103,111,127,165,168,185,193,200,242,268],"research":[20,86,137],"community.":[21],"However,":[22],"researchers":[23],"often":[24,53],"train":[25],"evaluate":[27],"new":[28,46,246],"models":[29],"on":[30,267],"small":[31],"or":[32],"outdated":[33],"datasets":[34],"that":[35,138,160,184,212,251],"do":[36],"not":[37],"reflect":[38,110],"current":[40,112],"state":[41,113],"of":[42,114,167,195,199,208,223,230],"knowledge,":[43],"thereby":[44],"disregarding":[45],"information":[47,254],"rich":[50],"textual":[51,131],"content":[52,132],"linked":[54],"to":[55,63,109,232],"graphs.":[57],"As":[58],"a":[59,72,155,245],"result,":[60],"many":[61],"opportunities":[62],"leverage":[64],"these":[65,213],"dimensions":[66],"are":[67],"missed.":[68],"We":[69,101,125,153],"introduce":[70],"WikiRAG,":[71],"framework":[73,95],"evaluation":[78,222],"derived":[79],"Wikidata":[81,115],"Wikipedia,":[83,135],"which":[84],"enables":[85],"integrating":[87,171],"retrieval":[88,150],"techniques":[89],"large":[91],"language":[92,172],"models.":[93],"Our":[94],"combines":[96],"following":[98],"contributions:":[99],"(i)":[100],"revisit":[102],"Wikidata5M":[104],"dataset":[105,128,169],"by":[106,189],"updating":[107],"providing":[117],"automated":[118],"tools":[119],"its":[121],"periodic":[122],"maintenance.":[123],"(ii)":[124],"enrich":[126],"with":[129],"long-form":[130],"sourced":[133],"enabling":[136],"goes":[139],"beyond":[140],"traditional":[141],"structures":[143],"shallow":[145],"text":[146],"methods":[147,210],"toward":[148],"dense":[149],"techniques.":[151],"(iii)":[152],"propose":[154],"simple":[156],"yet":[157],"effective":[158],"baseline":[159],"leverages":[161],"retrieval-augmented":[162],"generation,":[163],"demonstrating":[164],"utility":[166],"model":[173],"capabilities":[174],"link":[176,235],"prediction.":[177],"The":[178,256],"revised":[179],"dataset,":[180],"coined":[181],"Wikidata5M-RE,":[182],"shows":[183,227],"original":[186],"grew":[188],"roughly":[190],"50%":[191],"in":[192,234,248],"number":[194],"edges,":[196],"while":[197],"10%":[198],"edges":[201],"have":[202,263],"been":[203,264],"removed.":[204],"A":[205],"comparative":[206],"analysis":[207],"classic":[209],"demonstrates":[211],"changes":[214],"can":[215],"impact":[216],"downstream":[217],"evaluation.":[219],"Finally,":[220],"our":[221],"WikiRAG's":[224],"KGC":[225],"method":[226],"improvement":[229],"up":[231],"9%":[233],"accuracy":[237],"over":[238],"state-of-the-art":[239],"baselines,":[240],"setting":[241],"stage":[243],"avenue":[247],"uses":[252],"deep":[253],"extraction.":[255],"source":[257],"code,":[258],"data,":[259],"other":[261],"artifacts":[262],"made":[265],"available":[266],"project":[269],"website:":[270],"https://github.com/colab-nyuad/WikiRAG":[271]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}