{"id":"https://openalex.org/W4412888616","doi":"https://doi.org/10.18653/v1/2025.findings-acl.306","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","display_name":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888616","doi":"https://doi.org/10.18653/v1/2025.findings-acl.306"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.306","pdf_url":"https://aclanthology.org/2025.findings-acl.306.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: ACL 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-acl.306.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101501969","display_name":"Hui Huang","orcid":"https://orcid.org/0000-0003-4474-7037"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Huang","raw_affiliation_strings":["Faculty of Computing , Harbin Institute of Technology , Harbin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing , Harbin Institute of Technology , Harbin , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039569339","display_name":"Xingyuan Bu","orcid":"https://orcid.org/0000-0002-6445-4306"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyuan Bu","raw_affiliation_strings":["School of Computer Science , Beijing Institute of Technology , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Beijing Institute of Technology , Beijing , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongli Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Zhou","raw_affiliation_strings":["Faculty of Computing , Harbin Institute of Technology , Harbin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing , Harbin Institute of Technology , Harbin , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021663654","display_name":"Yingqi Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingqi Qu","raw_affiliation_strings":["Baidu Inc. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc. , Beijing , China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413406","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-2323-3475"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Baidu Inc. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc. , Beijing , China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108053327","display_name":"Muyun Yang","orcid":"https://orcid.org/0000-0002-5940-0266"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muyun Yang","raw_affiliation_strings":["Faculty of Computing , Harbin Institute of Technology , Harbin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing , Harbin Institute of Technology , Harbin , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009288767","display_name":"Bing Xu","orcid":"https://orcid.org/0000-0001-8779-0823"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Xu","raw_affiliation_strings":["Faculty of Computing , Harbin Institute of Technology , Harbin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing , Harbin Institute of Technology , Harbin , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038560914","display_name":"Tiejun Zhao","orcid":"https://orcid.org/0000-0002-1754-5416"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Zhao","raw_affiliation_strings":["Faculty of Computing , Harbin Institute of Technology , Harbin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing , Harbin Institute of Technology , Harbin , China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":193.7062,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9999272,"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":"5880","last_page":"5895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11762","display_name":"Law, Economics, and Judicial Systems","score":0.6782000064849854,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11762","display_name":"Law, Economics, and Judicial Systems","score":0.6782000064849854,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11496","display_name":"Credit Risk and Financial Regulations","score":0.6159999966621399,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.6089000105857849,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5300212502479553},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5090624690055847},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.33497345447540283},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18323567509651184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13787522912025452},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10954892635345459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5300212502479553},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5090624690055847},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.33497345447540283},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18323567509651184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13787522912025452},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10954892635345459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.306","pdf_url":"https://aclanthology.org/2025.findings-acl.306.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.306","pdf_url":"https://aclanthology.org/2025.findings-acl.306.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1912045422","display_name":null,"funder_award_id":"62376075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7320519987","display_name":null,"funder_award_id":"62276077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8973983596","display_name":null,"funder_award_id":"62376076","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/W4412888616.pdf","grobid_xml":"https://content.openalex.org/works/W4412888616.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"a":[4,93],"growing":[5],"trend":[6],"of":[7,17,52],"utilizing":[8],"Large":[9],"Language":[10],"Model":[11],"(LLM)":[12],"to":[13,37],"evaluate":[14],"the":[15,31,58,86,98],"quality":[16],"other":[18],"LLMs.Many":[19],"studies":[20],"have":[21],"fine-tuned":[22,59,87],"judge":[23,33,60,88],"models":[24,34,61],"based":[25],"on":[26,65],"opensource":[27],"LLMs":[28],"for":[29],"evaluation.While":[30],"finetuned":[32],"are":[35],"claimed":[36],"achieve":[38,62],"comparable":[39],"evaluation":[40],"capability":[41],"with":[42],"GPT-4,":[43,71],"in":[44],"this":[45],"work,":[46],"we":[47],"conduct":[48],"an":[49],"empirical":[50],"study":[51],"LLM-as-a-Judge.Our":[53],"findings":[54],"indicate":[55],"that":[56,85],"although":[57],"high":[63],"performance":[64],"in-domain":[66],"test":[67],"sets,":[68],"even":[69],"surpassing":[70],"they":[72],"underperform":[73],"GPT-4":[74],"across":[75],"several":[76],"dimensions,":[77],"including":[78],"generalizability,":[79],"fairness":[80],"and":[81],"adaptability.We":[82],"also":[83],"reveal":[84],"model":[89],"inherently":[90],"operates":[91],"as":[92],"task-specific":[94],"classifier,":[95],"consequently":[96],"imposing":[97],"limitations":[99],"1":[100],".":[101]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":10}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
