{"id":"https://openalex.org/W7140124652","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.125","title":"Aggregating Crowd of LLMs for Cost-Effective Data Annotation","display_name":"Aggregating Crowd of LLMs for Cost-Effective Data Annotation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140124652","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.125"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.125","pdf_url":"https://aclanthology.org/2026.findings-eacl.125.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.125.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130341657","display_name":"Jiacheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Liu","raw_affiliation_strings":["University Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130368512","display_name":"Xiaofeng Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Hou","raw_affiliation_strings":["University Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2407","last_page":"2419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.7268999814987183,"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":0.7268999814987183,"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/T11719","display_name":"Data Quality and Management","score":0.048500001430511475,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.042100001126527786,"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":0.5751000046730042},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2842000126838684},{"id":"https://openalex.org/keywords/crowd-sourcing","display_name":"Crowd sourcing","score":0.26190000772476196},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.23890000581741333}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536899983882904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2694999873638153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C3018396927","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowd sourcing","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23890000581741333},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23649999499320984}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.125","pdf_url":"https://aclanthology.org/2026.findings-eacl.125.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.125","pdf_url":"https://aclanthology.org/2026.findings-eacl.125.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7557400493","display_name":null,"funder_award_id":"62441225","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140124652.pdf","grobid_xml":"https://content.openalex.org/works/W7140124652.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"shown":[8],"promise":[9],"for":[10,115,124],"automated":[11],"data":[12,118],"annotation,":[13],"yet":[14],"reliance":[15],"on":[16],"expensive":[17],"commercial":[18],"models":[19],"like":[20],"GPT-4":[21],"limits":[22],"accessibility.This":[23],"paper":[24],"rigorously":[25],"evaluates":[26],"the":[27,70,111,122],"potential":[28],"of":[29,72,113],"open-source":[30],"smaller":[31],"LLMs":[32],"(sLLMs)":[33],"as":[34],"a":[35,39],"cost-effective":[36],"alternative.We":[37],"introduce":[38],"new":[40],"benchmark":[41],"dataset,":[42],"Multidisciplinary":[43],"Open":[44],"Research":[45],"Data":[46],"(MORD),":[47],"comprising":[48],"12,277":[49],"annotated":[50],"sentence":[51],"segments":[52],"from":[53,77],"1,500":[54],"scholarly":[55],"articles":[56],"across":[57],"five":[58],"research":[59],"domains,":[60],"to":[61,68,105,128],"systematically":[62],"assess":[63],"sLLM":[64,95],"performance.We":[65],"further":[66],"propose":[67],"build":[69],"Crowd":[71],"LLMs,":[73],"which":[74],"aggregates":[75],"annotations":[76,96],"multiple":[78],"sLLMs":[79,89,114],"using":[80],"label":[81],"aggregation":[82,126],"algorithms.This":[83],"approach":[84],"not":[85],"only":[86],"outperforms":[87],"individual":[88],"but":[90],"also":[91],"reveals":[92],"that":[93],"combining":[94],"with":[97],"human":[98],"crowd":[99],"labels":[100],"yields":[101],"superior":[102],"results":[103],"compared":[104],"either":[106],"method":[107],"alone.Our":[108],"findings":[109],"highlight":[110],"viability":[112],"democratizing":[116],"high-quality":[117],"annotation":[119],"while":[120],"underscoring":[121],"need":[123],"tailored":[125],"methods":[127],"fully":[129],"realize":[130],"their":[131],"potential.":[132]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}