{"id":"https://openalex.org/W4415316405","doi":"https://doi.org/10.1145/3767695.3769508","title":"Can We Hide Machines in the Crowd? Quantifying Equivalence in LLM-in-the-loop Annotation Tasks","display_name":"Can We Hide Machines in the Crowd? Quantifying Equivalence in LLM-in-the-loop Annotation Tasks","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4415316405","doi":"https://doi.org/10.1145/3767695.3769508"},"language":"en","primary_location":{"id":"doi:10.1145/3767695.3769508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769508","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767695.3769508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiaman He","orcid":"https://orcid.org/0009-0007-2817-7675"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Jiaman He","raw_affiliation_strings":["RMIT University, Naarm/Melbourne, Australia"],"raw_orcid":"https://orcid.org/0009-0007-2817-7675","affiliations":[{"raw_affiliation_string":"RMIT University, Naarm/Melbourne, Australia","institution_ids":["https://openalex.org/I82951845","https://openalex.org/I4210095297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060028891","display_name":"Zikang Leng","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zikang Leng","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6789-4780","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059558616","display_name":"Dana McKay","orcid":"https://orcid.org/0000-0001-7522-1842"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Dana McKay","raw_affiliation_strings":["RMIT University, Naarm/Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7522-1842","affiliations":[{"raw_affiliation_string":"RMIT University, Naarm/Melbourne, Australia","institution_ids":["https://openalex.org/I82951845","https://openalex.org/I4210095297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083881309","display_name":"Damiano Spina","orcid":"https://orcid.org/0000-0001-9913-433X"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Damiano Spina","raw_affiliation_strings":["RMIT University, Naarm/Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9913-433X","affiliations":[{"raw_affiliation_string":"RMIT University, Naarm/Melbourne, Australia","institution_ids":["https://openalex.org/I82951845","https://openalex.org/I4210095297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053547177","display_name":"Johanne R. Trippas","orcid":"https://orcid.org/0000-0002-7801-0239"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Johanne R Trippas","raw_affiliation_strings":["RMIT University, Naarm/Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7801-0239","affiliations":[{"raw_affiliation_string":"RMIT University, Naarm/Melbourne, Australia","institution_ids":["https://openalex.org/I82951845","https://openalex.org/I4210095297"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13616774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"426","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9944000244140625,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9944000244140625,"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":0.9801999926567078,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9538000226020813,"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/annotation","display_name":"Annotation","score":0.8302000164985657},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6560999751091003},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.6553000211715698},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/movielens","display_name":"MovieLens","score":0.3734999895095825},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.33340001106262207}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8302000164985657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710099995136261},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6560999751091003},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.6553000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555899977684021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5060999989509583},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C2776156558","wikidata":"https://www.wikidata.org/wiki/Q4353746","display_name":"MovieLens","level":4,"score":0.3734999895095825},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C2986817661","wikidata":"https://www.wikidata.org/wiki/Q185698","display_name":"Research methodology","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3767695.3769508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769508","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.06658","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06658","pdf_url":"https://arxiv.org/pdf/2510.06658","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3767695.3769508","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767695.3769508","pdf_url":null,"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 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Many":[0],"evaluations":[1],"of":[2,15,74,118],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"in":[7,147,155],"text":[8],"annotation":[9,60,68],"focus":[10],"primarily":[11],"on":[12,92],"the":[13,16,76,98,138],"correctness":[14],"output,":[17],"typically":[18],"comparing":[19],"model-generated":[20],"labels":[21],"to":[22,40,128],"human-annotated":[23],"''ground":[24],"truth''":[25],"using":[26],"standard":[27],"performance":[28],"metrics.":[29],"In":[30],"contrast,":[31],"our":[32],"study":[33],"moves":[34],"beyond":[35],"effectiveness":[36],"alone.":[37],"We":[38,124],"aim":[39],"explore":[41],"how":[42],"labeling":[43],"decisions--by":[44],"both":[45],"humans":[46],"and":[47,97,133,135],"LLMs--can":[48],"be":[49,72],"statistically":[50,141],"evaluated":[51],"across":[52],"individuals.":[53],"Rather":[54],"than":[55],"treating":[56],"LLMs":[57,64],"purely":[58],"as":[59,65],"systems,":[61],"we":[62,85],"approach":[63,127],"an":[66,111],"alternative":[67],"mechanism":[69],"that":[70,137],"may":[71],"capable":[73],"mimicking":[75],"subjective":[77],"judgments":[78],"made":[79],"by":[80],"humans.":[81],"To":[82],"assess":[83],"this,":[84],"develop":[86],"a":[87,116,144],"statistical":[88],"evaluation":[89,107],"method":[90,108],"based":[91],"Krippendorff's":[93],"alpha,":[94],"paired":[95],"bootstrapping,":[96],"Two":[99],"One-Sided":[100],"t-Tests":[101],"(TOST)":[102],"equivalence":[103],"test":[104],"procedure.":[105],"This":[106],"tests":[109],"whether":[110],"LLM":[112,139],"can":[113],"blend":[114],"into":[115],"group":[117],"human":[119,145],"annotators":[120],"without":[121],"being":[122],"distinguishable.":[123],"apply":[125],"this":[126],"two":[129],"datasets,":[130],"MovieLens":[131,148],"100K":[132,149],"PolitiFact,":[134],"find":[136],"is":[140],"indistinguishable":[142],"from":[143],"annotator":[146],"(p":[150,157],"=":[151,158],"0.004),":[152],"but":[153],"not":[154],"PolitiFact":[156],"0.155),":[159],"highlighting":[160],"task-dependent":[161],"differences.":[162]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-18T00:00:00"}