{"id":"https://openalex.org/W4417301015","doi":"https://doi.org/10.48550/arxiv.2505.12546","title":"Extracting memorized pieces of (copyrighted) books from open-weight language models","display_name":"Extracting memorized pieces of (copyrighted) books from open-weight language models","publication_year":2025,"publication_date":"2025-05-18","ids":{"openalex":"https://openalex.org/W4417301015","doi":"https://doi.org/10.48550/arxiv.2505.12546"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.12546","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.12546","pdf_url":"https://arxiv.org/pdf/2505.12546","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.12546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064217008","display_name":"A. Feder Cooper","orcid":"https://orcid.org/0000-0002-4892-681X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cooper, A. Feder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029160764","display_name":"Aaron Gokaslan","orcid":"https://orcid.org/0000-0002-3575-2961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lemley, Mark A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393194","display_name":"Ahmed Ahmed","orcid":"https://orcid.org/0000-0003-0827-9512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Casasola, Allison","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042134422","display_name":"Amy Cyphert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed, Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041869459","display_name":"Christopher De","orcid":"https://orcid.org/0000-0002-3610-2696"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gokaslan, Aaron","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088186426","display_name":"Mark A. Lemley","orcid":"https://orcid.org/0000-0002-2944-0582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cyphert, Amy B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102614290","display_name":"Daniel E. Ho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"De Sa, Christopher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025255782","display_name":"Percy Liang","orcid":"https://orcid.org/0000-0002-0458-6139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho, Daniel E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025255782","display_name":"Percy Liang","orcid":"https://orcid.org/0000-0002-0458-6139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Percy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5064217008"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13851","display_name":"Law, AI, and Intellectual Property","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"}},"topics":[{"id":"https://openalex.org/T13851","display_name":"Law, AI, and Intellectual Property","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"}},{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.10100000351667404,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06930000334978104,"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/memorization","display_name":"Memorization","score":0.933899998664856},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5616000294685364},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45210000872612},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3440000116825104},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31839999556541443}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.933899998664856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578000009059906},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3440000116825104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3127000033855438},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.12546","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.12546","pdf_url":"https://arxiv.org/pdf/2505.12546","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2505.12546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.12546","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.12546","pdf_url":"https://arxiv.org/pdf/2505.12546","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Plaintiffs":[0],"and":[1,44,64,80,123],"defendants":[2],"in":[3,28,101,104],"copyright":[4,160],"lawsuits":[5],"over":[6,69],"generative":[7],"AI":[8],"often":[9],"make":[10],"sweeping,":[11],"opposing":[12],"claims":[13],"about":[14],"the":[15,40,124,136,142],"extent":[16],"to":[17,53,61,84],"which":[18,58],"large":[19],"language":[20],"models":[21],"(LLMs)":[22],"memorize":[23,96],"protected":[24],"expression":[25],"from":[26],"books":[27,63,98],"their":[29],"training":[30],"data.":[31],"We":[32,151],"show":[33,73],"that":[34,74,91,131,165],"these":[35],"polarized":[36],"positions":[37],"dramatically":[38],"oversimplify":[39],"relationship":[41],"between":[42],"memorization":[43,55,75,127],"copyright.":[45],"To":[46],"do":[47,94],"so,":[48],"we":[49,59,72,89],"develop":[50],"a":[51],"technique":[52],"measure":[54],"of":[56],"books,":[57,119],"apply":[60],"200":[62],"14":[65],"open-weight":[66],"LLMs.":[67],"Through":[68],"3000":[70],"experiments,":[71],"varies":[76],"both":[77],"by":[78],"model":[79],"book.":[81],"With":[82],"respect":[83],"our":[85,154],"specific":[86],"extraction":[87],"methodology,":[88],"find":[90],"most":[92,97],"LLMs":[93],"not":[95,163],"--":[99],"either":[100,168],"whole":[102,137],"or":[103],"part;":[105],"however,":[106],"there":[107],"are":[108],"notable":[109],"exceptions.":[110],"For":[111],"instance,":[112],"Llama":[113],"3.1":[114],"70B":[115],"entirely":[116],"memorizes":[117],"some":[118],"like":[120],"Harry":[121],"Potter":[122],"Sorcerer's":[125],"Stone;":[126],"is":[128],"so":[129],"extensive":[130],"one":[132],"can":[133],"deterministically":[134],"extract":[135],"book":[138],"almost":[139],"verbatim":[140],"using":[141],"book's":[143],"first":[144],"few":[145],"words":[146],"as":[147],"an":[148],"initial":[149],"prompt.":[150],"discuss":[152],"why":[153],"results":[155],"have":[156],"significant":[157],"implications":[158],"for":[159],"cases,":[161],"though":[162],"ones":[164],"unambiguously":[166],"favor":[167],"side.":[169]},"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}