{"id":"https://openalex.org/W4416034245","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1036","title":"The Progress Illusion: Revisiting meta-evaluation standards of LLM evaluators","display_name":"The Progress Illusion: Revisiting meta-evaluation standards of LLM evaluators","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034245","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1036"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1036","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1036","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1036.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1036.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308525","display_name":"Tianruo Rose Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianruo Rose Xu","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vedant Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vedant Gaur","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011342505","display_name":"Liu Leqi","orcid":"https://orcid.org/0000-0002-9707-4529"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu Leqi","raw_affiliation_strings":["University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120308526","display_name":"Tanya Goyal","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanya Goyal","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.47368421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19033","last_page":"19043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.07980000227689743,"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"}},"topics":[{"id":"https://openalex.org/T10102","display_name":"scientometrics and bibliometrics research","score":0.07980000227689743,"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/T12010","display_name":"Evaluation and Performance Assessment","score":0.0746999979019165,"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/T10206","display_name":"Meta-analysis and systematic reviews","score":0.03849999979138374,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2757999897003174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2743000090122223},{"id":"https://openalex.org/keywords/agency","display_name":"Agency (philosophy)","score":0.26910001039505005},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2680000066757202},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25859999656677246}],"concepts":[{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.4862000048160553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3190999925136566},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3009999990463257},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2849000096321106},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28459998965263367},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2596000134944916},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1036","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1036","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1036.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1036","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1036","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1036.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034245.pdf","grobid_xml":"https://content.openalex.org/works/W4416034245.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM":[0,26,45,75,151],"judges":[1],"have":[2],"gained":[3],"popularity":[4],"as":[5],"an":[6],"inexpensive":[7],"and":[8,153],"performant":[9],"substitute":[10],"for":[11,156],"human":[12,79],"evaluation.However,":[13],"we":[14,41,100],"observe":[15],"that":[16,50,65,73,105,118,128],"the":[17,22,85,103,106,109,136],"meta-evaluation":[18,138,152],"setting":[19,49],"in":[20,36,68],"which":[21],"reliability":[23],"of":[24,44,93,108],"these":[25],"evaluators":[27,46,120],"is":[28,30],"established":[29],"substantially":[31],"different":[32],"from":[33],"their":[34],"use":[35],"model":[37,111],"development.To":[38],"address":[39],"this,":[40],"revisit":[42],"metaevaluations":[43],"under":[47],"a":[48,90],"more":[51],"closely":[52],"aligns":[53],"with":[54,78,96,149],"practice":[55],"by":[56],"examining":[57],"evaluators'":[58],"ability":[59],"to":[60,113],"distinguish":[61],"test":[62,126],"system":[63],"pairs":[64],"are":[66,81],"closer":[67],"capability.Our":[69],"fine-grained":[70],"approach":[71],"shows":[72,146],"all":[74],"evaluator's":[76],"correlations":[77],"judgments":[80],"concerningly":[82],"low":[83],"when":[84],"models":[86],"perform":[87,122],"similarly,":[88],"showcasing":[89],"key":[91],"limitation":[92],"current":[94,150],"norms.Equipped":[95],"this":[97],"better":[98],"methodology,":[99],"next":[101],"analyze":[102],"impact":[104],"choice":[107],"reference":[110],"makes":[112],"LLMas-a-judge":[114],"evaluator":[115],"performance.We":[116],"show":[117],"single-reference":[119],"only":[121],"well":[123],"at":[124],"ranking":[125],"systems":[127],"fall":[129],"within":[130],"particular":[131],"capability":[132],"ranges,":[133],"even":[134],"if":[135],"standard":[137],"reports":[139],"high":[140],"overall":[141],"correlation.Taken":[142],"together,":[143],"our":[144],"analysis":[145],"critical":[147],"issues":[148],"recommend":[154],"avenues":[155],"improvement.":[157]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-11-08T00:00:00"}