{"id":"https://openalex.org/W4412945174","doi":"https://doi.org/10.18653/v1/2025.acl-long.782","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","display_name":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945174","doi":"https://doi.org/10.18653/v1/2025.acl-long.782"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.782","doi":"https://doi.org/10.18653/v1/2025.acl-long.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.782","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2025.acl-long.782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023044414","display_name":"Nitay Calderon","orcid":"https://orcid.org/0009-0009-9196-9821","observed_orcids":["https://orcid.org/0009-0009-9196-9821"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nitay Calderon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054952724","display_name":"Roi Reichart","orcid":"https://orcid.org/0000-0001-6918-0554","observed_orcids":["https://orcid.org/0000-0001-6918-0554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roi Reichart","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089112142","display_name":"Rotem Dror","orcid":"https://orcid.org/0000-0002-9433-8410","observed_orcids":["https://orcid.org/0000-0002-9433-8410"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rotem Dror","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":159.8337,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.99967802,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"16051","last_page":"16081"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.8179000020027161,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T13643","display_name":"Artificial Intelligence in Law","score":0.8179000020027161,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"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/T13309","display_name":"Reliability and Agreement in Measurement","score":0.023900000378489494,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14115","display_name":"Legal processes and jurisprudence","score":0.020400000736117363,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.7649999856948853},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7559999823570251},{"id":"https://openalex.org/keywords/annotation-quality","display_name":"annotation quality","score":0.33000001311302185}],"concepts":[{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6579388380050659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5560235977172852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3230605125427246},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.782","doi":"https://doi.org/10.18653/v1/2025.acl-long.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.782","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.10970","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.10970","pdf_url":"https://arxiv.org/pdf/2501.10970","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.10970","doi":"https://doi.org/10.48550/arxiv.2501.10970","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.10970","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.782","doi":"https://doi.org/10.18653/v1/2025.acl-long.782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.782","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415316405","https://openalex.org/W4400104877","https://openalex.org/W7164884660","https://openalex.org/W4389523857","https://openalex.org/W4396831993","https://openalex.org/W7125351155","https://openalex.org/W7164832585","https://openalex.org/W7155247400","https://openalex.org/W4379255800","https://openalex.org/W7131791800"],"abstract_inverted_index":{"The":[0],"\"LLM-as-an-annotator\"":[1],"and":[2,13,38,48,98,105,122,125,131,156,172],"\"LLM-as-a-judge\"":[3],"paradigms":[4],"employ":[5],"Large":[6],"Language":[7],"Models":[8],"(LLMs)":[9],"as":[10,148],"annotators,":[11],"judges,":[12],"evaluators":[14],"in":[15,28,33,44],"tasks":[16],"traditionally":[17],"performed":[18],"by":[19],"humans.":[20],"LLM":[21,91,103],"annotations":[22],"are":[23],"widely":[24],"used,":[25],"not":[26],"only":[27,81],"NLP":[29],"research":[30],"but":[31],"also":[32],"fields":[34],"like":[35],"medicine,":[36],"psychology,":[37],"social":[39],"science.":[40],"Despite":[41],"their":[42],"role":[43],"shaping":[45],"study":[46,168],"results":[47,136],"insights,":[49],"there":[50],"is":[51],"no":[52],"standard":[53],"or":[54],"rigorous":[55,171],"procedure":[56],"to":[57,88],"determine":[58],"whether":[59],"LLMs":[60,130,139,146,153],"can":[61,140],"replace":[62,142],"human":[63],"annotators.":[64],"In":[65],"this":[66,167],"paper,":[67],"we":[68,94,111,154],"propose":[69],"a":[70,82,96,113],"novel":[71],"statistical":[72],"procedure,":[73,110],"the":[74,151],"Alternative":[75],"Annotator":[76],"Test":[77],"(alt-test),":[78],"that":[79,138,157],"requires":[80],"modest":[83],"subset":[84],"of":[85,116,120,162],"annotated":[86],"examples":[87],"justify":[89],"using":[90],"annotations.":[92],"Additionally,":[93],"introduce":[95],"versatile":[97],"interpretable":[99],"measure":[100],"for":[101],"comparing":[102],"annotators":[104],"judges.":[106],"To":[107],"demonstrate":[108],"our":[109],"curated":[112],"diverse":[114],"collection":[115],"ten":[117],"datasets,":[118],"consisting":[119],"language":[121],"vision-language":[123],"tasks,":[124],"conducted":[126],"experiments":[127],"with":[128,144],"six":[129],"four":[132],"prompting":[133,158],"techniques.":[134],"Our":[135],"show":[137],"sometimes":[141],"humans":[143],"closed-source":[145],"(such":[147],"GPT-4o),":[149],"outperforming":[150],"open-source":[152],"examine,":[155],"techniques":[159],"yield":[160],"judges":[161],"varying":[163],"quality.":[164],"We":[165],"hope":[166],"encourages":[169],"more":[170],"reliable":[173],"practices.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":7}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}