{"id":"https://openalex.org/W4401808240","doi":"https://doi.org/10.1007/s00607-024-01331-9","title":"Large language models: a new approach for privacy policy analysis at scale","display_name":"Large language models: a new approach for privacy policy analysis at scale","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401808240","doi":"https://doi.org/10.1007/s00607-024-01331-9"},"language":"en","primary_location":{"id":"doi:10.1007/s00607-024-01331-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00607-024-01331-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00607-024-01331-9.pdf","source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00607-024-01331-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100609859","display_name":"David Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-0911-4608"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Rodriguez","raw_affiliation_strings":["ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079262837","display_name":"Ian A. Yang","orcid":"https://orcid.org/0000-0001-8338-1993"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Yang","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Forbes Ave, Pittsburgh, PA, 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Forbes Ave, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090208333","display_name":"Jos\u00e9 M. Del \u00c1lamo","orcid":"https://orcid.org/0000-0002-6513-0303"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Jose M. Del Alamo","raw_affiliation_strings":["ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETSI Telecomunicaci\u00f3n, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081563886","display_name":"Norman Sadeh","orcid":"https://orcid.org/0000-0003-4829-5533"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norman Sadeh","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Forbes Ave, Pittsburgh, PA, 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Forbes Ave, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090208333"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":37.4042,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.99821047,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"106","issue":"12","first_page":"3879","last_page":"3903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9722999930381775,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9552000164985657,"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/computer-science","display_name":"Computer science","score":0.7792890071868896},{"id":"https://openalex.org/keywords/privacy-policy","display_name":"Privacy policy","score":0.7132149338722229},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5112099647521973},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4915545880794525},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.475988507270813},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4523825943470001},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4446987807750702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4411216080188751},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4400930106639862},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.42490291595458984},{"id":"https://openalex.org/keywords/privacy-law","display_name":"Privacy law","score":0.4174205958843231},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4008501470088959},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.37526455521583557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3623559772968292},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3588101863861084},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33673906326293945},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.17622950673103333},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1101619303226471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792890071868896},{"id":"https://openalex.org/C102938260","wikidata":"https://www.wikidata.org/wiki/Q1999831","display_name":"Privacy policy","level":3,"score":0.7132149338722229},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5112099647521973},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4915545880794525},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.475988507270813},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4523825943470001},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4446987807750702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4411216080188751},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4400930106639862},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.42490291595458984},{"id":"https://openalex.org/C141972696","wikidata":"https://www.wikidata.org/wiki/Q1247836","display_name":"Privacy law","level":4,"score":0.4174205958843231},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4008501470088959},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.37526455521583557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3623559772968292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3588101863861084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33673906326293945},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17622950673103333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1101619303226471},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00607-024-01331-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00607-024-01331-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00607-024-01331-9.pdf","source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00607-024-01331-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00607-024-01331-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00607-024-01331-9.pdf","source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G7186414377","display_name":null,"funder_award_id":"MCIN/AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322138","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F7296444849","display_name":"Ministerio de Universidades","ror":"https://ror.org/03zcny908"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401808240.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1972675781","https://openalex.org/W1981276685","https://openalex.org/W2075876574","https://openalex.org/W2250861254","https://openalex.org/W2293557490","https://openalex.org/W2517394750","https://openalex.org/W2612622960","https://openalex.org/W2615266218","https://openalex.org/W2732750509","https://openalex.org/W2759177743","https://openalex.org/W2963070937","https://openalex.org/W2970728484","https://openalex.org/W3012939329","https://openalex.org/W3108807663","https://openalex.org/W4229452781","https://openalex.org/W4246562710","https://openalex.org/W4303614602","https://openalex.org/W4320009668","https://openalex.org/W4323528060","https://openalex.org/W4362452929","https://openalex.org/W4366417848","https://openalex.org/W4385595397","https://openalex.org/W4385734156","https://openalex.org/W4388764805","https://openalex.org/W4389518664","https://openalex.org/W4389523957"],"related_works":["https://openalex.org/W576625533","https://openalex.org/W2470776051","https://openalex.org/W3016483802","https://openalex.org/W1598195095","https://openalex.org/W2017433517","https://openalex.org/W2027335090","https://openalex.org/W1535304801","https://openalex.org/W1493227450","https://openalex.org/W2280711247","https://openalex.org/W2243362394"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"number":[2],"and":[3,9,14,30,64,69,83,100,114,117,140,152],"dynamic":[4],"nature":[5],"of":[6,61,66,104,121,129,138,156,161,168],"web":[7],"sites":[8],"mobile":[10,67],"applications":[11],"present":[12],"regulators":[13],"app":[15],"store":[16],"operators":[17],"with":[18,27,59,215],"significant":[19],"challenges":[20],"when":[21],"it":[22],"comes":[23],"to":[24,42,48,70,89,94,204,229],"enforcing":[25],"compliance":[26,51],"applicable":[28],"privacy":[29,50,57,73,130,169,231],"data":[31,122],"protection":[32],"laws.":[33],"Over":[34],"the":[35,62,91,102,127,136,162,187,201,206],"past":[36],"several":[37],"years,":[38],"people":[39],"have":[40,79],"turned":[41],"Natural":[43],"Language":[44,106],"Processing":[45],"(NLP)":[46],"techniques":[47,78,164],"automate":[49],"analysis":[52,60,233],"(e.g.,":[53],"comparing":[54],"statements":[55],"in":[56,126,186,218],"policies":[58],"code":[63],"behavior":[65],"apps)":[68],"answer":[71],"people\u2019s":[72],"questions.":[74],"Traditionally,":[75],"these":[76,157,190],"NLP":[77],"relied":[80],"on":[81,135,165,189],"labor-intensive":[82],"potentially":[84],"error-prone":[85],"manual":[86],"annotation":[87],"processes":[88],"build":[90],"corpora":[92,167],"necessary":[93],"train":[95,205],"them.":[96],"This":[97,148,178,192],"article":[98],"explores":[99],"evaluates":[101],"use":[103],"Large":[105],"Models":[107],"(LLMs)":[108],"as":[109],"an":[110,173],"alternative":[111],"for":[112],"effectively":[113],"efficiently":[115],"identifying":[116],"categorizing":[118],"a":[119,225],"variety":[120],"practice":[123],"disclosures":[124],"found":[125],"text":[128],"policies.":[131],"Specifically,":[132],"we":[133],"report":[134],"performance":[137,193],"ChatGPT":[139],"Llama":[141],"2,":[142],"two":[143],"particularly":[144,226],"popular":[145],"LLM-based":[146],"tools.":[147],"includes":[149],"engineering":[150],"prompts":[151],"evaluating":[153],"different":[154],"configurations":[155],"LLM":[158],"techniques.":[159],"Evaluation":[160],"resulting":[163],"well-known":[166],"policy":[170,232],"annotations":[171],"yields":[172],"F1":[174],"score":[175,179],"exceeding":[176],"93%.":[177],"is":[180,194],"higher":[181],"than":[182],"scores":[183],"reported":[184,217],"earlier":[185],"literature":[188],"benchmarks.":[191],"obtained":[195],"at":[196,234],"minimal":[197],"marginal":[198],"cost":[199,202],"(excluding":[200],"required":[203],"foundational":[207],"models":[208],"themselves).":[209],"These":[210],"results,":[211],"which":[212],"are":[213],"consistent":[214],"those":[216],"other":[219],"domains,":[220],"suggest":[221],"that":[222],"LLMs":[223],"offer":[224],"promising":[227],"approach":[228],"automated":[230],"scale.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}