{"id":"https://openalex.org/W7166555405","doi":"https://doi.org/10.18653/2026.findings-emnlp.2337","title":"An Empirical Analysis of Factual Errors in Human-Written Text and Its Application to Factual Error Detection","display_name":"An Empirical Analysis of Factual Errors in Human-Written Text and Its Application to Factual Error Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166555405","doi":"https://doi.org/10.18653/2026.findings-emnlp.2337"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.2337","doi":"https://doi.org/10.18653/2026.findings-emnlp.2337","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2337","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2337.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.2337.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108670604","display_name":"Kazuma Iwamoto","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuma Iwamoto","raw_affiliation_strings":["Nikkei Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nikkei Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018128634","display_name":"Kazumasa Omura","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazumasa Omura","raw_affiliation_strings":["Nikkei Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nikkei Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034011295","display_name":"Shotaro Ishihara","orcid":"https://orcid.org/0009-0001-0366-6807","observed_orcids":["https://orcid.org/0009-0001-0366-6807"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shotaro Ishihara","raw_affiliation_strings":["Nikkei Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nikkei Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41733361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"50250","last_page":"50264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7470999956130981,"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":0.7470999956130981,"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":0.22169999778270721,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.009600000455975533,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/human-written-text","display_name":"human-written text","score":0.9539999961853027},{"id":"https://openalex.org/keywords/factual-errors","display_name":"factual errors","score":0.6539999842643738},{"id":"https://openalex.org/keywords/error-taxonomy","display_name":"error taxonomy","score":0.6959999799728394},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8320000171661377},{"id":"https://openalex.org/keywords/hallucination-detection","display_name":"hallucination detection","score":0.6639999747276306},{"id":"https://openalex.org/keywords/synthetic-test-cases","display_name":"synthetic test cases","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689000129699707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6455000042915344},{"id":"https://openalex.org/C204160518","wikidata":"https://www.wikidata.org/wiki/Q122653","display_name":"Numeral system","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946999788284302},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C11192451","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Stylometry","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2565999925136566}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.2337","doi":"https://doi.org/10.18653/2026.findings-emnlp.2337","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2337","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2337.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.27959","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.27959","pdf_url":"https://arxiv.org/pdf/2606.27959","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.27959","doi":"https://doi.org/10.48550/arxiv.2606.27959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27959","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.2337","doi":"https://doi.org/10.18653/2026.findings-emnlp.2337","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2337","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2337.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.7580825090408325,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166555405.pdf","grobid_xml":"https://content.openalex.org/works/W7166555405.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387995128","https://openalex.org/W4391013695","https://openalex.org/W7133214006","https://openalex.org/W7197207393","https://openalex.org/W4378469989","https://openalex.org/W7140121407","https://openalex.org/W4392019759","https://openalex.org/W4389520333","https://openalex.org/W4401023869","https://openalex.org/W4406592198"],"abstract_inverted_index":{"Factual":[0],"Error":[1],"Detection":[2],"(FED),":[3],"which":[4,112],"is":[5,88],"the":[6,27,52,121,126,156,161,171,181],"task":[7,162],"of":[8,30,54,72,79,85,129,153,174],"identifying":[9],"factually":[10],"incorrect":[11],"spans":[12],"in":[13,57,116,200],"a":[14,50,70,82,164],"given":[15],"text,":[16],"has":[17,37,60],"long":[18],"been":[19,61],"recognized":[20],"as":[21,106,147],"an":[22],"important":[23],"research":[24,35],"problem.However,":[25],"with":[26,184],"rapid":[28],"rise":[29],"large":[31],"language":[32],"models":[33],"(LLMs),":[34],"attention":[36],"shifted":[38],"toward":[39],"factual":[40,55,74,191],"errors":[41,56,75],"specific":[42],"to":[43,90],"LLM-generated":[44],"text":[45,59,86],"(hallucinations)":[46],"and":[47,93,109,137,198],"their":[48],"detection.As":[49],"result,":[51],"detection":[53,168],"human-written":[58,92],"relatively":[62],"neglected.To":[63],"address":[64,190],"this":[65,201],"gap,":[66],"we":[67,123,194],"first":[68],"distill":[69],"taxonomy":[71],"humaninduced":[73],"by":[76,167],"analyzing":[77],"corrections":[78],"newspaper":[80],"articles,":[81],"representative":[83],"source":[84],"that":[87,100,142],"guaranteed":[89],"be":[91],"contains":[94],"few":[95],"grammatical":[96],"errors.Our":[97],"analysis":[98,166],"revealed":[99,170],"there":[101],"are":[102,113],"characteristic":[103],"categories":[104],"such":[105,146],"kanji":[107],"misconversions":[108],"unit":[110],"errors,":[111,192],"not":[114],"focused":[115],"existing":[117],"hallucination":[118],"benchmarks.Based":[119],"on":[120,132,155],"taxonomy,":[122],"then":[124],"evaluate":[125],"FED":[127],"capability":[128],"vanilla":[130],"LLMs":[131,145],"synthesized":[133],"realistic":[134],"test":[135],"cases":[136],"real":[138],"corrections.Experimental":[139],"results":[140],"demonstrated":[141],"even":[143],"high-performance":[144],"GPT-5.4achieved":[148],"only":[149],"word-level":[150],"F1":[151],"score":[152],"52%":[154],"synthetic":[157],"evaluation":[158],"data,":[159],"highlighting":[160],"difficulty.Furthermore,":[163],"detailed":[165],"difficulty":[169],"current":[172],"state":[173],"FED.*":[175],"This":[176],"work":[177],"was":[178,183],"conducted":[179],"while":[180],"author":[182],"Nikkei":[185],"Inc.1":[186],"Proofreading":[187],"might":[188],"also":[189],"but":[193],"distinguish":[195],"between":[196],"proofreading":[197],"revising":[199],"sense.":[202]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-06-30T00:00:00"}