{"id":"https://openalex.org/W3176075285","doi":"https://doi.org/10.1145/3462741.3466809","title":"Bigger Isn\u2019t Better: The Ethical and Scientific Vices of Extra-Large Datasets in Language Models","display_name":"Bigger Isn\u2019t Better: The Ethical and Scientific Vices of Extra-Large Datasets in Language Models","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3176075285","doi":"https://doi.org/10.1145/3462741.3466809","mag":"3176075285"},"language":"en","primary_location":{"id":"doi:10.1145/3462741.3466809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462741.3466809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"13th ACM Web Science Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://philpapers.org/archive/GOEBIB.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060105605","display_name":"Trystan S. Goetze","orcid":"https://orcid.org/0000-0002-3435-3264"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Trystan S. Goetze","raw_affiliation_strings":["Dalhousie University, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071707646","display_name":"Darren Abramson","orcid":"https://orcid.org/0000-0001-5916-6927"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Darren Abramson","raw_affiliation_strings":["Dalhousie University, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060105605"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":1.2169,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82953244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9948999881744385,"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":0.9681000113487244,"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":0.7291967272758484},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.717158317565918},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5890844464302063},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5414896011352539},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4152357578277588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2925911545753479},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.10875052213668823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291967272758484},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.717158317565918},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5890844464302063},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5414896011352539},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4152357578277588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2925911545753479},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.10875052213668823},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3462741.3466809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462741.3466809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"13th ACM Web Science Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:175082","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:philarchive.org/rec/GOEBIB","is_oa":true,"landing_page_url":"https://philarchive.org/rec/GOEBIB","pdf_url":"https://philpapers.org/archive/GOEBIB.pdf","source":{"id":"https://openalex.org/S4306402130","display_name":"PhilPapers (PhilPapers Foundation)","issn_l":null,"issn":null,"is_oa":false,"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":"info:eu-repo/semantics/article"},{"id":"pmh:oai:philpapers.org/rec/GOEBIB","is_oa":false,"landing_page_url":"https://philpapers.org/rec/GOEBIB","pdf_url":null,"source":{"id":"https://openalex.org/S4306402131","display_name":"PhilPapers (PhilPapers Foundation)","issn_l":null,"issn":null,"is_oa":false,"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:philarchive.org/rec/GOEBIB","is_oa":true,"landing_page_url":"https://philarchive.org/rec/GOEBIB","pdf_url":"https://philpapers.org/archive/GOEBIB.pdf","source":{"id":"https://openalex.org/S4306402130","display_name":"PhilPapers (PhilPapers Foundation)","issn_l":null,"issn":null,"is_oa":false,"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":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.5,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G404729310","display_name":null,"funder_award_id":"BPF-162659","funder_id":"https://openalex.org/F4320334617","funder_display_name":"Social Sciences and Humanities Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320334617","display_name":"Social Sciences and Humanities Research Council of Canada","ror":"https://ror.org/04j5jqy92"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3176075285.pdf","grobid_xml":"https://content.openalex.org/works/W3176075285.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W155107352","https://openalex.org/W1563143755","https://openalex.org/W1585231348","https://openalex.org/W1985574895","https://openalex.org/W2007018772","https://openalex.org/W2036484382","https://openalex.org/W2042882066","https://openalex.org/W2137872373","https://openalex.org/W2334700554","https://openalex.org/W2398514781","https://openalex.org/W2561529111","https://openalex.org/W2607719644","https://openalex.org/W2610105073","https://openalex.org/W2777647957","https://openalex.org/W2788481061","https://openalex.org/W2788969155","https://openalex.org/W2802642435","https://openalex.org/W2898695519","https://openalex.org/W2911227954","https://openalex.org/W2957654274","https://openalex.org/W2996908057","https://openalex.org/W3018929370","https://openalex.org/W3121257585","https://openalex.org/W3121336520","https://openalex.org/W3133702157","https://openalex.org/W3134889244","https://openalex.org/W4310936740"],"related_works":["https://openalex.org/W2384667405","https://openalex.org/W2389266787","https://openalex.org/W2363885542","https://openalex.org/W2387206255","https://openalex.org/W2355570285","https://openalex.org/W2364958354","https://openalex.org/W2352797113","https://openalex.org/W2372137583","https://openalex.org/W1548050717","https://openalex.org/W2374872591"],"abstract_inverted_index":{"The":[0],"use":[1,151],"of":[2,11,33,39,46,53,66,76,106,137,146],"language":[3,34,114],"models":[4,35],"in":[5,31,113,122,129,152],"Web":[6],"applications":[7],"and":[8,13,69,110,126,133],"other":[9],"areas":[10],"computing":[12],"business":[14],"have":[15],"grown":[16],"significantly":[17],"over":[18],"the":[19,29,51,64,90,94,130,138],"last":[20],"five":[21],"years.":[22],"One":[23],"reason":[24],"for":[25,148,159],"this":[26,77],"growth":[27],"is":[28,56],"improvement":[30],"performance":[32],"on":[36,73,89],"a":[37,43,54,143],"number":[38],"benchmarks":[40],"\u2014":[41],"but":[42],"side":[44],"effect":[45],"these":[47],"advances":[48],"has":[49],"been":[50],"adoption":[52],"\u201cbigger":[55],"always":[57],"better\u201d":[58],"paradigm":[59,78],"when":[60,156],"it":[61],"comes":[62],"to":[63,81,96,150],"size":[65],"training,":[67],"testing,":[68],"challenge":[70,97],"datasets.":[71],"Drawing":[72],"previous":[74],"criticisms":[75],"as":[79],"applied":[80],"large":[82,154],"training":[83],"datasets":[84,98,155],"crawled":[85],"from":[86],"pre-existing":[87],"text":[88],"Web,":[91],"we":[92],"extend":[93],"critique":[95],"custom-created":[99],"by":[100],"crowdworkers.":[101],"We":[102,140],"present":[103,142],"several":[104],"sets":[105],"criticisms,":[107],"where":[108],"ethical":[109],"scientific":[111],"issues":[112],"model":[115],"research":[116,131],"reinforce":[117],"each":[118],"other:":[119],"labour":[120],"injustices":[121],"crowdwork,":[123],"dataset":[124],"quality":[125],"inscrutability,":[127],"inequities":[128],"community,":[132],"centralized":[134],"corporate":[135],"control":[136],"technology.":[139],"also":[141],"new":[144],"type":[145],"tool":[147],"researchers":[149],"examining":[153],"evaluating":[157],"them":[158],"quality.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
