{"id":"https://openalex.org/W4416035179","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1765","title":"Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models","display_name":"Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035179","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1765"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1765","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1765","pdf_url":"https://aclanthology.org/2025.emnlp-main.1765.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1765.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031309131","display_name":"Sina J. Semnani","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sina Semnani","raw_affiliation_strings":["Computer Science Department Stanford University , Stanford , CA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Stanford University , Stanford , CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039931233","display_name":"Jirayu Burapacheep","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jirayu Burapacheep","raw_affiliation_strings":["Computer Science Department Stanford University , Stanford , CA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Stanford University , Stanford , CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050749526","display_name":"Arpandeep Khatua","orcid":"https://orcid.org/0000-0001-9406-2322"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arpandeep Khatua","raw_affiliation_strings":["Computer Science Department Stanford University , Stanford , CA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Stanford University , Stanford , CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120056812","display_name":"Thanawan Atchariyachanvanit","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thanawan Atchariyachanvanit","raw_affiliation_strings":["Computer Science Department Stanford University , Stanford , CA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Stanford University , Stanford , CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602037","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-1243-0177"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Computer Science Department Stanford University , Stanford , CA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Stanford University , Stanford , CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002419188","display_name":"Monica S. Lam","orcid":"https://orcid.org/0000-0002-1205-1302"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monica Lam","raw_affiliation_strings":["Computer Science Department Stanford University , Stanford , CA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department Stanford University , Stanford , CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031309131"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38662871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34827","last_page":"34854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9329000115394592,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9329000115394592,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.029999999329447746,"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":0.005100000184029341,"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-model","display_name":"Language model","score":0.32440000772476196},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31290000677108765},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2851000130176544},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27709999680519104},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.27469998598098755},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.2718000113964081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159000039100647},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3905999958515167},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1765","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1765","pdf_url":"https://aclanthology.org/2025.emnlp-main.1765.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1765","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1765","pdf_url":"https://aclanthology.org/2025.emnlp-main.1765.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035179.pdf","grobid_xml":"https://content.openalex.org/works/W4416035179.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Wikipedia":[0,87,120,135,180],"is":[1,29,34],"the":[2,53,103,115,160],"largest":[3],"open":[4],"knowledge":[5,196],"corpus,":[6],"widely":[7],"used":[8],"worldwide":[9],"and":[10,22,36,51,96,147,181],"serving":[11],"as":[12],"a":[13,45,82,176,189],"key":[14],"resource":[15],"for":[16,79],"training":[17],"large":[18],"language":[19],"models":[20],"(LLMs)":[21],"retrieval-augmented":[23],"generation":[24],"(RAG)":[25],"systems.Ensuring":[26],"its":[27],"accuracy":[28],"therefore":[30],"critical.But":[31],"how":[32,37],"accurate":[33],"Wikipedia,":[35],"can":[38,187],"we":[39,112,127],"improve":[40,195],"it?We":[41],"focus":[42],"on":[43,154],"inconsistencies,":[44],"specific":[46],"type":[47],"of":[48,55,106,118,133,145,149,168,179],"factual":[49],"inaccuracy,":[50],"introduce":[52],"task":[54],"corpus-level":[56],"inconsistency":[57],"detection.We":[58],"present":[59],"CLAIRE,":[60,95],"an":[61,166],"agentic":[62],"system":[63,164],"that":[64,129,173,182],"combines":[65],"LLM":[66],"reasoning":[67],"with":[68,76,85,109,124,140],"retrieval":[69],"to":[70,192],"surface":[71],"potentially":[72],"inconsistent":[73],"claims":[74],"along":[75],"contextual":[77],"evidence":[78],"human":[80,110],"review.In":[81],"user":[83],"study":[84],"experienced":[86],"editors,":[88],"87.5%":[89],"reported":[90],"higher":[91],"confidence":[92],"when":[93],"using":[94],"participants":[97],"identified":[98],"64.7%":[99],"more":[100],"inconsistencies":[101,141],"in":[102],"same":[104],"amount":[105],"time.Combining":[107],"CLAIRE":[108,186],"annotation,":[111],"contribute":[113],"WIKICOLLIDE,":[114],"first":[116],"benchmark":[117],"real":[119],"inconsistencies.Using":[121],"random":[122],"sampling":[123],"CLAIRE-assisted":[125],"analysis,":[126],"find":[128],"at":[130,198],"least":[131],"3.3%":[132],"English":[134],"facts":[136],"contradict":[137],"another":[138],"fact,":[139],"propagating":[142],"into":[143],"7.3%":[144],"FEVEROUS":[146],"4.0%":[148],"AmbigQA":[150],"examples.Benchmarking":[151],"strong":[152],"baselines":[153],"this":[155],"dataset":[156],"reveals":[157],"substantial":[158],"headroom:":[159],"best":[161],"fully":[162],"automated":[163],"achieves":[165],"AUROC":[167],"only":[169],"75.1%.Our":[170],"results":[171],"show":[172],"contradictions":[174],"are":[175],"measurable":[177],"component":[178],"LLM-based":[183],"systems":[184],"like":[185],"provide":[188],"practical":[190],"tool":[191],"help":[193],"editors":[194],"consistency":[197],"scale.":[199],"1":[200]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-11-08T00:00:00"}