{"id":"https://openalex.org/W4376643691","doi":"https://doi.org/10.1145/3597307","title":"Biases in Large Language Models: Origins, Inventory, and Discussion","display_name":"Biases in Large Language Models: Origins, Inventory, and Discussion","publication_year":2023,"publication_date":"2023-05-16","ids":{"openalex":"https://openalex.org/W4376643691","doi":"https://doi.org/10.1145/3597307"},"language":"en","primary_location":{"id":"doi:10.1145/3597307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597307","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597307","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3597307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026648049","display_name":"Roberto Navigli","orcid":"https://orcid.org/0000-0003-3831-9706"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Navigli","raw_affiliation_strings":["Sapienza University of Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3831-9706","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056508457","display_name":"Simone Conia","orcid":"https://orcid.org/0000-0002-6238-7816"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Conia","raw_affiliation_strings":["Sapienza University of Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6238-7816","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023817571","display_name":"Bj\u00f6rn Ro\u00df","orcid":"https://orcid.org/0000-0003-2717-3705"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Ross","raw_affiliation_strings":["University of Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2717-3705","affiliations":[{"raw_affiliation_string":"University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":44.3291,"has_fulltext":true,"cited_by_count":339,"citation_normalized_percentile":{"value":0.99897903,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"15","issue":"2","first_page":"1","last_page":"21"},"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":0.9991999864578247,"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/T13629","display_name":"Text Readability and Simplification","score":0.9696000218391418,"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":0.8047510981559753},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.6760455369949341},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5936741232872009},{"id":"https://openalex.org/keywords/gender-bias","display_name":"Gender bias","score":0.539103627204895},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.536107063293457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.513738751411438},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.45062851905822754},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36879366636276245},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.32838577032089233},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18669959902763367},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10888653993606567},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07819750905036926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047510981559753},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.6760455369949341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5936741232872009},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.539103627204895},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.536107063293457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513738751411438},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.45062851905822754},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36879366636276245},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32838577032089233},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18669959902763367},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10888653993606567},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07819750905036926},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3597307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597307","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597307","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1696393","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1696393","pdf_url":"https://iris.uniroma1.it/bitstream/11573/1696393/1/Navigli_Biases_2023.pdf","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/0c46779d-8656-45c9-90c1-f1d0dfd9072e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/352548259/Biases_in_Large_NAVIGLI_DOA02022023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Navigli, R, Conia, S & Ross, B 2023, 'Biases in Large Language Models: Origins, Inventory and Discussion', Journal of Data and Information Quality, vol. 15, no. 2, 10, pp. 1-21. https://doi.org/10.1145/3597307","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/0c46779d-8656-45c9-90c1-f1d0dfd9072e","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.1145/3597307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/0c46779d-8656-45c9-90c1-f1d0dfd9072e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0c46779d-8656-45c9-90c1-f1d0dfd9072e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Navigli, R, Conia, S & Ross, B 2023, 'Biases in Large Language Models: Origins, Inventory and Discussion', Journal of Data and Information Quality, vol. 15, no. 2, 10, pp. 1-21. https://doi.org/10.1145/3597307","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3597307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597307","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597307","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"Horizon2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4628848537","display_name":null,"funder_award_id":"726487","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376643691.pdf","grobid_xml":"https://content.openalex.org/works/W4376643691.grobid-xml"},"referenced_works_count":121,"referenced_works":["https://openalex.org/W1500693574","https://openalex.org/W1566289585","https://openalex.org/W2014516359","https://openalex.org/W2022597878","https://openalex.org/W2065157922","https://openalex.org/W2075778137","https://openalex.org/W2103018059","https://openalex.org/W2120699290","https://openalex.org/W2126851059","https://openalex.org/W2142222368","https://openalex.org/W2147520877","https://openalex.org/W2151170651","https://openalex.org/W2157171669","https://openalex.org/W2323140206","https://openalex.org/W2405607598","https://openalex.org/W2436001372","https://openalex.org/W2620949368","https://openalex.org/W2752446824","https://openalex.org/W2769358515","https://openalex.org/W2795975316","https://openalex.org/W2799146523","https://openalex.org/W2832191606","https://openalex.org/W2888628862","https://openalex.org/W2908195148","https://openalex.org/W2917410007","https://openalex.org/W2944827918","https://openalex.org/W2950888501","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963381846","https://openalex.org/W2965373594","https://openalex.org/W2972413484","https://openalex.org/W2981852735","https://openalex.org/W2981869278","https://openalex.org/W3013937328","https://openalex.org/W3022421338","https://openalex.org/W3030163527","https://openalex.org/W3032553678","https://openalex.org/W3034723486","https://openalex.org/W3034782826","https://openalex.org/W3034999214","https://openalex.org/W3035032094","https://openalex.org/W3035296331","https://openalex.org/W3035390927","https://openalex.org/W3037831233","https://openalex.org/W3042185737","https://openalex.org/W3047137977","https://openalex.org/W3090483338","https://openalex.org/W3101118213","https://openalex.org/W3101767999","https://openalex.org/W3105882417","https://openalex.org/W3118781290","https://openalex.org/W3123015728","https://openalex.org/W3125640539","https://openalex.org/W3133702157","https://openalex.org/W3133764719","https://openalex.org/W3137010024","https://openalex.org/W3154079701","https://openalex.org/W3156649430","https://openalex.org/W3159259047","https://openalex.org/W3168251909","https://openalex.org/W3168771811","https://openalex.org/W3169262646","https://openalex.org/W3169483174","https://openalex.org/W3170956458","https://openalex.org/W3172335055","https://openalex.org/W3173529047","https://openalex.org/W3173677700","https://openalex.org/W3175765954","https://openalex.org/W3176477796","https://openalex.org/W3177189402","https://openalex.org/W3184144760","https://openalex.org/W3185341429","https://openalex.org/W3188983256","https://openalex.org/W3190186724","https://openalex.org/W3190457554","https://openalex.org/W3191409995","https://openalex.org/W3193147816","https://openalex.org/W3196248941","https://openalex.org/W3197071999","https://openalex.org/W3202415077","https://openalex.org/W3203196106","https://openalex.org/W3213432108","https://openalex.org/W3217152367","https://openalex.org/W4205374619","https://openalex.org/W4206118214","https://openalex.org/W4206136559","https://openalex.org/W4206285331","https://openalex.org/W4224308101","https://openalex.org/W4224928727","https://openalex.org/W4224929277","https://openalex.org/W4226227340","https://openalex.org/W4226395792","https://openalex.org/W4226399820","https://openalex.org/W4229005866","https://openalex.org/W4245698581","https://openalex.org/W4247456889","https://openalex.org/W4281621415","https://openalex.org/W4285059449","https://openalex.org/W4285060763","https://openalex.org/W4285155368","https://openalex.org/W4285192810","https://openalex.org/W4285210581","https://openalex.org/W4285236281","https://openalex.org/W4285244508","https://openalex.org/W4285286514","https://openalex.org/W4285306804","https://openalex.org/W4287888528","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4307474756","https://openalex.org/W4308760226","https://openalex.org/W4309088836","https://openalex.org/W4311642023","https://openalex.org/W4319453056","https://openalex.org/W4322718191","https://openalex.org/W6788175385","https://openalex.org/W6810081322","https://openalex.org/W6811129797","https://openalex.org/W6811340617","https://openalex.org/W6939216866"],"related_works":["https://openalex.org/W2377237701","https://openalex.org/W2360099860","https://openalex.org/W1583826057","https://openalex.org/W2352463596","https://openalex.org/W2380850119","https://openalex.org/W2101450440","https://openalex.org/W2383675217","https://openalex.org/W2521871361","https://openalex.org/W2011417417","https://openalex.org/W4281757053"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,54],"introduce":[4,33],"and":[5,84,97],"discuss":[6],"the":[7,13,21,39,43,56,64,99],"pervasive":[8],"issue":[9],"of":[10,23,45,59,102],"bias":[11,40,61],"in":[12,63],"large":[14],"language":[15,68],"models":[16,69],"that":[17,37,47],"are":[18],"currently":[19],"at":[20],"core":[22],"mainstream":[24],"approaches":[25],"to":[26,77,82,87],"Natural":[27],"Language":[28],"Processing":[29],"(NLP).":[30],"We":[31,89],"first":[32],"data":[34],"selection":[35],"bias,":[36],"is,":[38],"caused":[41],"by":[42,67],"choice":[44],"texts":[46],"make":[48],"up":[49],"a":[50],"training":[51],"corpus.":[52],"Then,":[53],"survey":[55],"different":[57],"types":[58,101],"social":[60],"evidenced":[62],"text":[65],"generated":[66],"trained":[70],"on":[71,94],"such":[72],"corpora,":[73],"ranging":[74],"from":[75,79,85],"gender":[76],"age,":[78],"sexual":[80],"orientation":[81],"ethnicity,":[83],"religion":[86],"culture.":[88],"conclude":[90],"with":[91],"directions":[92],"focused":[93],"measuring,":[95],"reducing,":[96],"tackling":[98],"aforementioned":[100],"bias.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":71},{"year":2025,"cited_by_count":164},{"year":2024,"cited_by_count":89},{"year":2023,"cited_by_count":15}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2023-05-17T00:00:00"}