{"id":"https://openalex.org/W4390684469","doi":"https://doi.org/10.1162/coli_a_00508","title":"Common Flaws in Running Human Evaluation Experiments in NLP","display_name":"Common Flaws in Running Human Evaluation Experiments in NLP","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390684469","doi":"https://doi.org/10.1162/coli_a_00508"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00508","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00508","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00508/2207528/coli_a_00508.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00508/2207528/coli_a_00508.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032668442","display_name":"Craig Thomson","orcid":"https://orcid.org/0000-0002-1602-4694"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]},{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["GB","IE"],"is_corresponding":false,"raw_author_name":"Craig Thomson","raw_affiliation_strings":["ADAPT, Dublin City University and University of Aberdeen. c.thomson.nlp@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT, Dublin City University and University of Aberdeen. c.thomson.nlp@gmail.com","institution_ids":["https://openalex.org/I195460627","https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005939553","display_name":"Ehud Reiter","orcid":"https://orcid.org/0000-0002-7548-9504"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ehud Reiter","raw_affiliation_strings":["Department of Computing Science, University of Aberdeen. e.reiter@abdn.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Aberdeen. e.reiter@abdn.ac.uk","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010118897","display_name":"Anja Belz","orcid":"https://orcid.org/0000-0002-0552-8096"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]},{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["GB","IE"],"is_corresponding":false,"raw_author_name":"Anya Belz","raw_affiliation_strings":["ADAPT, Dublin City University and University of Aberdeen. anya.belz@adaptcentre.ie"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT, Dublin City University and University of Aberdeen. anya.belz@adaptcentre.ie","institution_ids":["https://openalex.org/I195460627","https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5746,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84032847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"50","issue":"2","first_page":"795","last_page":"805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9987000226974487,"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/T10260","display_name":"Software Engineering Research","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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":0.8167091012001038},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5746651887893677},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5493823289871216},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5426263809204102},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5026822090148926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4553734064102173},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44729313254356384},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4320669174194336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36092668771743774},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17772957682609558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167091012001038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5746651887893677},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5493823289871216},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5426263809204102},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5026822090148926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553734064102173},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44729313254356384},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4320669174194336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36092668771743774},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17772957682609558},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":3,"locations":[{"id":"doi:10.1162/coli_a_00508","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00508","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00508/2207528/coli_a_00508.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:aura.abdn.ac.uk:2164/23764","is_oa":true,"landing_page_url":"https://abdn.elsevierpure.com/en/publications/bdae6575-848e-4639-ae80-0a7f6dbe0f02","pdf_url":null,"source":{"id":"https://openalex.org/S4306400966","display_name":"Aberdeen University Research Archive (Aberdeen University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I195460627","host_organization_name":"University of Aberdeen","host_organization_lineage":["https://openalex.org/I195460627"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal article"},{"id":"pmh:oai:doaj.org/article:03a212ea394c484eb1adf69faff20ab0","is_oa":false,"landing_page_url":"https://doaj.org/article/03a212ea394c484eb1adf69faff20ab0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"Computational Linguistics, Vol 50, Iss 2 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00508","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00508","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00508/2207528/coli_a_00508.pdf","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G474172064","display_name":"ReproHum: Investigating Reproducibility of Human Evaluations in Natural Language Processing","funder_award_id":"EP/V05645X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7233328857","display_name":null,"funder_award_id":"EP/V05645X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390684469.pdf","grobid_xml":"https://content.openalex.org/works/W4390684469.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2040975718","https://openalex.org/W2144981148","https://openalex.org/W2147976241","https://openalex.org/W2194370442","https://openalex.org/W3092501936","https://openalex.org/W3109862485","https://openalex.org/W3129394092","https://openalex.org/W3139277020","https://openalex.org/W3153873661","https://openalex.org/W3159892921","https://openalex.org/W3167109678","https://openalex.org/W4224280420","https://openalex.org/W4289522081","https://openalex.org/W4301737008","https://openalex.org/W4313560086","https://openalex.org/W4378908626","https://openalex.org/W4382363179","https://openalex.org/W4385567251","https://openalex.org/W4386566537","https://openalex.org/W4402671955","https://openalex.org/W6799087104","https://openalex.org/W6810765986","https://openalex.org/W6851198971","https://openalex.org/W6969461231"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W2961085424","https://openalex.org/W3125889879","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W3046451053","https://openalex.org/W2097909533","https://openalex.org/W3125188128"],"abstract_inverted_index":{"Abstract":[0],"While":[1],"conducting":[2],"a":[3,27],"coordinated":[4],"set":[5],"of":[6,9,37,63,93,110,126],"repeat":[7],"runs":[8],"human":[10],"evaluation":[11,95],"experiments":[12,96],"in":[13,18,69],"NLP,":[14],"we":[15,22,33,39],"discovered":[16],"flaws":[17,38],"every":[19],"single":[20],"experiment":[21],"selected":[23],"for":[24,90],"inclusion":[25],"via":[26],"systematic":[28],"process.":[29],"In":[30],"this":[31],"squib,":[32],"describe":[34],"the":[35,47,91,108],"types":[36],"discovered,":[40],"which":[41],"include":[42],"coding":[43],"errors":[44],"(e.g.,":[45,59,73],"loading":[46],"wrong":[48],"system":[49],"outputs":[50],"to":[51,54,106],"evaluate),":[52],"failure":[53],"follow":[55],"standard":[56],"scientific":[57],"practice":[58],"ad":[60],"hoc":[61],"exclusion":[62],"participants":[64],"and":[65,67,121,123],"responses),":[66],"mistakes":[68],"reported":[70,74],"numerical":[71],"results":[72],"numbers":[75],"not":[76],"matching":[77],"experimental":[78],"data).":[79],"If":[80],"these":[81],"problems":[82],"are":[83],"widespread,":[84],"it":[85],"would":[86],"have":[87],"worrying":[88],"implications":[89],"rigor":[92],"NLP":[94],"as":[97],"currently":[98],"conducted.":[99],"We":[100],"discuss":[101],"what":[102],"researchers":[103],"can":[104],"do":[105],"reduce":[107],"occurrence":[109],"such":[111],"flaws,":[112],"including":[113],"pre-registration,":[114],"better":[115],"code":[116],"development":[117],"practices,":[118],"increased":[119],"testing":[120],"piloting,":[122],"post-publication":[124],"addressing":[125],"errors.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}