{"id":"https://openalex.org/W3082136315","doi":"https://doi.org/10.1145/3437963.3441809","title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","display_name":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","publication_year":2021,"publication_date":"2021-03-06","ids":{"openalex":"https://openalex.org/W3082136315","doi":"https://doi.org/10.1145/3437963.3441809","mag":"3082136315"},"language":"en","primary_location":{"id":"doi:10.1145/3437963.3441809","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437963.3441809","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441809","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 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036477705","display_name":"Dara Bahri","orcid":"https://orcid.org/0000-0003-0144-2911"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dara Bahri","raw_affiliation_strings":["Google Research, Mountain View, CA, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103069680","display_name":"Yi Tay","orcid":"https://orcid.org/0000-0001-6896-4496"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Tay","raw_affiliation_strings":["Google Research, Mountain View, CA, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744677","display_name":"Che Zheng","orcid":"https://orcid.org/0009-0008-0881-1023"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Che Zheng","raw_affiliation_strings":["Google Research, Mountain View, CA, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076280","display_name":"Cliff Brunk","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cliff Brunk","raw_affiliation_strings":["Google Research, Mountain View, CA, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000115067","display_name":"Donald Metzler","orcid":"https://orcid.org/0000-0003-4276-6269"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald Metzler","raw_affiliation_strings":["Google Research, Mountain View, CA, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068021191","display_name":"Andrew Tomkins","orcid":"https://orcid.org/0000-0002-1611-9255"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Tomkins","raw_affiliation_strings":["Google Research, Mountain View, CA, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036477705"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51134092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9871000051498413,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9614999890327454,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7764488458633423},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7312968373298645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6964555382728577},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.634428083896637},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5967631936073303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5800344944000244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5438064932823181},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4601678252220154},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4516793489456177},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4138123393058777},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.41333308815956116},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09861040115356445},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.08844888210296631},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0880577564239502},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06925460696220398}],"concepts":[{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7764488458633423},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7312968373298645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964555382728577},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.634428083896637},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5967631936073303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5800344944000244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5438064932823181},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4601678252220154},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4516793489456177},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4138123393058777},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.41333308815956116},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09861040115356445},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.08844888210296631},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0880577564239502},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06925460696220398},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3437963.3441809","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437963.3441809","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441809","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 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.13533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.13533","pdf_url":"https://arxiv.org/pdf/2008.13533","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3082136315","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2008.13533","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.13533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.13533","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":"doi:10.1145/3437963.3441809","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437963.3441809","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437963.3441809","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 14th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3082136315.pdf","grobid_xml":"https://content.openalex.org/works/W3082136315.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1544827683","https://openalex.org/W1685426458","https://openalex.org/W1993924397","https://openalex.org/W2066055909","https://openalex.org/W2101105183","https://openalex.org/W2101234009","https://openalex.org/W2160536005","https://openalex.org/W2402144811","https://openalex.org/W2406990858","https://openalex.org/W2509472099","https://openalex.org/W2525778437","https://openalex.org/W2798664956","https://openalex.org/W2889765309","https://openalex.org/W2896457183","https://openalex.org/W2925962955","https://openalex.org/W2938704169","https://openalex.org/W2947813521","https://openalex.org/W2948250930","https://openalex.org/W2948975009","https://openalex.org/W2949555952","https://openalex.org/W2951080837","https://openalex.org/W2963247666","https://openalex.org/W2963456134","https://openalex.org/W2963878748","https://openalex.org/W2965373594","https://openalex.org/W2968297680","https://openalex.org/W2969958763","https://openalex.org/W2973049837","https://openalex.org/W2980282514","https://openalex.org/W2993398598","https://openalex.org/W2997591727","https://openalex.org/W3030163527","https://openalex.org/W3034470897"],"related_works":["https://openalex.org/W2987090991","https://openalex.org/W3171229070","https://openalex.org/W2412589713","https://openalex.org/W3107573790","https://openalex.org/W2023161323","https://openalex.org/W2944958965","https://openalex.org/W1880728411","https://openalex.org/W2952749830","https://openalex.org/W2509601217","https://openalex.org/W130907108","https://openalex.org/W1548100229","https://openalex.org/W3119075751","https://openalex.org/W57372846","https://openalex.org/W3024617470","https://openalex.org/W22861983","https://openalex.org/W2911460956","https://openalex.org/W2807324141","https://openalex.org/W3214722511","https://openalex.org/W2293546719","https://openalex.org/W2910177331"],"abstract_inverted_index":{"Large":[0],"generative":[1],"language":[2],"models":[3],"such":[4],"as":[5,15,17,71],"GPT-2":[6,41],"are":[7],"well-known":[8],"for":[9],"their":[10,18],"ability":[11],"to":[12,63,78,99],"generate":[13],"text":[14,69],"well":[16,35],"utility":[19],"in":[20,93,109],"supervised":[21],"downstream":[22],"tasks":[23],"via":[24,57],"fine-tuning.":[25],"Its":[26],"prevalence":[27,102],"on":[28,131],"the":[29,44,101,110,126,132],"web,":[30,45],"however,":[31],"is":[32,52],"still":[33],"not":[34],"understood":[36],"-":[37],"if":[38],"we":[39,48,55,112],"run":[40],"detectors":[42],"across":[43],"what":[46],"will":[47],"find?":[49],"Our":[50],"work":[51],"twofold:":[53],"firstly":[54],"demonstrate":[56],"human":[58,66],"evaluation":[59],"that":[60],"classifiers":[61],"trained":[62],"discriminate":[64],"between":[65],"and":[67,103,116],"machine-generated":[68],"emerge":[70],"unsupervised":[72],"predictors":[73],"of":[74,90,105],"\"page":[75],"quality\",":[76],"able":[77],"detect":[79],"low":[80,106],"quality":[81,91,107],"content":[82],"without":[83],"any":[84],"training.":[85],"This":[86],"enables":[87],"fast":[88],"bootstrapping":[89],"indicators":[92],"a":[94],"low-resource":[95],"setting.":[96],"Secondly,":[97],"curious":[98],"understand":[100],"nature":[104],"pages":[108],"wild,":[111],"conduct":[113],"extensive":[114],"qualitative":[115],"quantitative":[117],"analysis":[118],"over":[119],"500":[120],"million":[121],"web":[122],"articles,":[123],"making":[124],"this":[125],"largest-scale":[127],"study":[128],"ever":[129],"conducted":[130],"topic.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}