{"id":"https://openalex.org/W4411522868","doi":"https://doi.org/10.1145/3728963","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","display_name":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411522868","doi":"https://doi.org/10.1145/3728963"},"language":"en","primary_location":{"id":"doi:10.1145/3728963","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728963","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3728963","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020056709","display_name":"Ruiqi Wang","orcid":"https://orcid.org/0009-0000-9336-0598"},"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":true,"raw_author_name":"Ruiqi Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104067103","display_name":"Jiyu Guo","orcid":"https://orcid.org/0009-0001-7055-0767"},"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":"Jiyu Guo","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061699251","display_name":"Cuiyun Gao","orcid":"https://orcid.org/0000-0003-4774-2434"},"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":"Cuiyun Gao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102957384","display_name":"Guodong Fan","orcid":"https://orcid.org/0000-0003-2031-0615"},"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":"Guodong Fan","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024635381","display_name":"Chun Yong Chong","orcid":"https://orcid.org/0000-0003-1164-0049"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Chun Yong Chong","raw_affiliation_strings":["Monash University Malaysia, Bandar Sunway, Malaysia"],"affiliations":[{"raw_affiliation_string":"Monash University Malaysia, Bandar Sunway, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006669765","display_name":"Xin Xia","orcid":"https://orcid.org/0000-0002-6302-3256"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xia","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020056709"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":62.0174,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.99896111,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"ISSTA","first_page":"1955","last_page":"1977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9811000227928162,"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/computer-science","display_name":"Computer science","score":0.6902151703834534},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6199035048484802},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5350033044815063},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47852954268455505},{"id":"https://openalex.org/keywords/scrutiny","display_name":"Scrutiny","score":0.45646917819976807},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4512466788291931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43579012155532837},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3788670301437378},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35249078273773193},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3416537344455719},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13323119282722473},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.1150522530078888},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09757295250892639}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902151703834534},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6199035048484802},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5350033044815063},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47852954268455505},{"id":"https://openalex.org/C2776050585","wikidata":"https://www.wikidata.org/wiki/Q7439360","display_name":"Scrutiny","level":2,"score":0.45646917819976807},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4512466788291931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43579012155532837},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3788670301437378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35249078273773193},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3416537344455719},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13323119282722473},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.1150522530078888},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09757295250892639},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728963","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728963","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3728963","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728963","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2930957955","https://openalex.org/W2970785793","https://openalex.org/W3034999214","https://openalex.org/W4221166942","https://openalex.org/W4387321091","https://openalex.org/W4391556029","https://openalex.org/W4407386473"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W1517524280"],"abstract_inverted_index":{"Recently,":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5,74],"been":[6],"deployed":[7],"to":[8,86,100,184,244],"tackle":[9],"various":[10],"software":[11],"engineering":[12],"(SE)":[13],"tasks":[14,121],"like":[15,64],"code":[16,32,172,174,177,219],"generation,":[17,175,222],"significantly":[18],"advancing":[19],"the":[20,27,191,207,231],"automation":[21],"of":[22,29,171,211,230],"SE":[23,120,134,169,278],"tasks.":[24,279],"However,":[25],"assessing":[26],"quality":[28],"these":[30,182,195],"LLM-generated":[31,60],"and":[33,46,54,161,176,213,221,237,248,263],"text":[34],"remains":[35,122],"challenging.":[36],"The":[37,200],"commonly":[38],"used":[39],"Pass@k":[40],"metric":[41],"necessitates":[42],"extensive":[43],"unit":[44],"tests":[45],"configured":[47],"environments,":[48],"demands":[49],"a":[50,81],"high":[51],"labor":[52],"cost,":[53],"is":[55],"not":[56],"suitable":[57],"for":[58,89,132,157],"evaluating":[59,133],"text.":[61],"Conventional":[62],"metrics":[63,107],"BLEU,":[65],"which":[66],"measure":[67],"only":[68],"lexical":[69],"rather":[70],"than":[71,105],"semantic":[72],"similarity,":[73],"also":[75],"come":[76],"under":[77],"scrutiny.":[78],"In":[79,124],"response,":[80],"new":[82],"trend":[83],"has":[84],"emerged":[85],"employ":[87],"LLMs":[88,154,243],"automated":[90],"evaluation,":[91,225],"known":[92],"as":[93],"LLM-as-a-judge.":[94],"These":[95],"LLM-as-a-judge":[96,130,146,269],"methods":[97,131,147,183,196,205,241,270],"are":[98],"claimed":[99],"better":[101],"mimic":[102],"human":[103,117,141,198,216,256,274],"assessment":[104],"conventional":[106,233],"without":[108],"relying":[109],"on":[110,137,166],"high-quality":[111],"reference":[112],"answers.":[113],"Nevertheless,":[114],"their":[115,138],"exact":[116],"alignment":[118,139],"in":[119,218,276],"unexplored.":[123],"this":[125],"paper,":[126],"we":[127,179,189,260],"empirically":[128],"explore":[129],"tasks,":[135],"focusing":[136],"with":[140,197,215],"judgments.":[142],"We":[143],"select":[144],"seven":[145],"that":[148,203,254,266],"utilize":[149],"general-purpose":[150],"LLMs,":[151],"alongside":[152],"two":[153],"specifically":[155],"fine-tuned":[156],"evaluation.":[158,199],"After":[159],"generating":[160],"manually":[162],"scoring":[163],"LLM":[164],"responses":[165],"three":[167],"recent":[168],"datasets":[170],"translation,":[173],"summarization,":[178],"then":[180],"prompt":[181,242],"evaluate":[185],"each":[186],"response.":[187],"Finally,":[188,259],"compare":[190],"scores":[192,217],"generated":[193],"by":[194],"results":[201],"indicate":[202],"output-based":[204,240],"reach":[206],"highest":[208],"Pearson":[209],"correlation":[210],"81.32":[212],"68.51":[214],"translation":[220],"achieving":[223],"near-human":[224],"noticeably":[226],"outperforming":[227],"ChrF++,":[228],"one":[229],"best":[232],"metrics,":[234],"at":[235],"34.23":[236],"64.92.":[238],"Such":[239],"output":[245],"judgments":[246],"directly,":[247],"exhibit":[249],"more":[250],"balanced":[251],"score":[252,257],"distributions":[253],"resemble":[255],"patterns.":[258],"provide":[261],"insights":[262],"implications,":[264],"concluding":[265],"current":[267],"state-of-the-art":[268],"can":[271],"potentially":[272],"replace":[273],"evaluations":[275],"certain":[277]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}