{"id":"https://openalex.org/W7140107456","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.45","title":"Personal Information Parroting in Language Models","display_name":"Personal Information Parroting in Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140107456","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.45"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.45","pdf_url":"https://aclanthology.org/2026.findings-eacl.45.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.45.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nishant Subramani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishant Subramani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kshitish Ghate","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kshitish Ghate","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mona T. Diab","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mona T. Diab","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"886","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.156700000166893,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.156700000166893,"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":0.12380000203847885,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.1193000003695488,"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/phone","display_name":"Phone","score":0.6327000260353088},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6039999723434448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5773000121116638},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.510200023651123},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.45590001344680786},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4431999921798706},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43810001015663147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6922000050544739},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037999749183655},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2994270382","wikidata":"https://www.wikidata.org/wiki/Q2296401","display_name":"Phone call","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C2988821698","wikidata":"https://www.wikidata.org/wiki/Q16338","display_name":"Personal computer","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.45","pdf_url":"https://aclanthology.org/2026.findings-eacl.45.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.45","pdf_url":"https://aclanthology.org/2026.findings-eacl.45.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140107456.pdf","grobid_xml":"https://content.openalex.org/works/W7140107456.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"language":[1],"models":[2,105],"(LM)":[3],"are":[4,69,130],"trained":[5],"on":[6],"large":[7],"scrapes":[8],"of":[9,14,20,58,61,106,128,141],"the":[10,31,49,73,77,82,86,89,95,116,135,142],"Web,":[11],"containing":[12],"millions":[13],"personal":[15],"information":[16],"(PI)":[17],"instances,":[18],"many":[19],"which":[21,47],"LMs":[22],"memorize,":[23],"increasing":[24],"privacy":[25],"risks.In":[26],"this":[27,101],"work,":[28],"we":[29,63,145],"develop":[30],"regexes":[32],"and":[33,44,120,126,154],"rules":[34],"(R&R)":[35],"detector":[36],"suite":[37,119],"to":[38,103,156],"detect":[39],"email":[40],"addresses,":[41,46],"phone":[42],"numbers,":[43],"IP":[45],"outperforms":[48],"best":[50],"regex-based":[51],"PI":[52,87,97,158],"detectors.On":[53],"a":[54],"manually":[55],"curated":[56],"set":[57],"483":[59],"instances":[60,143],"PI,":[62],"measure":[64],"memorization:":[65],"finding":[66],"that":[67,84,122,148],"13.6%":[68],"parroted":[70],"verbatim":[71],"by":[72],"Pythia-6.9bmodel,":[74],"i.e.,":[75],"when":[76],"model":[78,118,124],"is":[79],"prompted":[80],"with":[81,133],"tokens":[83],"precede":[85],"in":[88,115],"original":[90],"document,":[91],"greedy":[92],"decoding":[93],"generates":[94],"entire":[96],"span":[98],"exactly.We":[99],"expand":[100],"analysis":[102],"study":[104],"varying":[107],"sizes":[108],"(160M-6.9B)and":[109],"pretraining":[110,129,149],"time":[111],"steps":[112],"(70k-143k":[113],"iterations)":[114],"Pythia":[117],"find":[121],"both":[123],"size":[125],"amount":[127],"positively":[131],"correlated":[132],"memorization.Even":[134],"smallest":[136],"model,":[137],"Pythia-160m,":[138],"parrots":[139],"2.7%":[140],"exactly.Consequently,":[144],"strongly":[146],"recommend":[147],"datasets":[150],"be":[151],"aggressively":[152],"filtered":[153],"anonymized":[155],"minimize":[157],"parroting.":[159],"1":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-01T00:00:00"}