{"id":"https://openalex.org/W4407212961","doi":"https://doi.org/10.1145/3701716.3715265","title":"Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons","display_name":"Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4407212961","doi":"https://doi.org/10.1145/3701716.3715265"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715265","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715265","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715265","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103128873","display_name":"Renjun Hu","orcid":"https://orcid.org/0000-0002-1094-6890"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renjun Hu","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1094-6890","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187665","display_name":"Cheng Yi","orcid":"https://orcid.org/0000-0003-3075-8413"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cheng","raw_affiliation_strings":["Alibaba Cloud Computing, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3075-8413","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Libin Meng","orcid":"https://orcid.org/0009-0002-5979-5234"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libin Meng","raw_affiliation_strings":["Alibaba Cloud Computing, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-5979-5234","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114086942","display_name":"Jiaxin Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Xia","raw_affiliation_strings":["Alibaba Cloud Computing, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-9682-7320","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111334399","display_name":"Yi Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zong","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-3093-5957","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100534716","display_name":"Xing Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Shi","raw_affiliation_strings":["Alibaba Cloud Computing, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-5946-3187","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636012","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0002-3003-0150"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Alibaba Cloud Computing, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3003-0150","affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3651,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97377599,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"228","last_page":"237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9933000206947327,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9496999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7719640731811523},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7397087812423706},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.711883544921875},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6566354632377625},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5463956594467163},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5116344094276428},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38279759883880615},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3416292667388916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3320504128932953},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12282803654670715},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09782743453979492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719640731811523},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7397087812423706},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.711883544921875},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6566354632377625},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5463956594467163},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5116344094276428},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38279759883880615},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3416292667388916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3320504128932953},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12282803654670715},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09782743453979492},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3701716.3715265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715265","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715265","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.02988","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02988","pdf_url":"https://arxiv.org/pdf/2502.02988","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715265","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715265","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407212961.pdf","grobid_xml":"https://content.openalex.org/works/W4407212961.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2058373514","https://openalex.org/W2946609015","https://openalex.org/W3129831491","https://openalex.org/W4385572634","https://openalex.org/W4388722291","https://openalex.org/W4389520044","https://openalex.org/W4398133596","https://openalex.org/W4401042689","https://openalex.org/W4402670530","https://openalex.org/W4402671297","https://openalex.org/W4404780679","https://openalex.org/W4404781848","https://openalex.org/W4409892328"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W2593798266","https://openalex.org/W4385414918"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,36,110],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"has":[8],"opened":[9],"new":[10],"possibilities":[11],"for":[12,40,51,70,78,158],"their":[13],"adoption":[14],"as":[15],"evaluative":[16,62],"judges.":[17],"This":[18],"paper":[19],"introduces":[20],"Themis,":[21,41],"a":[22,33,134],"fine-tuned":[23],"LLM":[24],"judge":[25],"that":[26,81,116],"delivers":[27],"sophisticated":[28],"context-aware":[29],"evaluations.":[30],"We":[31,73,132,156],"provide":[32,143],"comprehensive":[34],"overview":[35],"the":[37,99,107,165],"development":[38,177],"pipeline":[39],"highlighting":[42],"its":[43],"scenario-dependent":[44],"evaluation":[45],"prompts":[46],"and":[47,106,153,161,169,176],"two":[48,75],"novel":[49],"methods":[50],"controlled":[52],"instruction":[53],"generation.":[54],"These":[55],"designs":[56],"enable":[57],"Themis":[58,82],"to":[59,172],"effectively":[60],"distill":[61],"skills":[63],"from":[64,120],"teacher":[65],"models,":[66],"while":[67],"retaining":[68],"flexibility":[69],"continuous":[71],"development.":[72],"introduce":[74],"human-labeled":[76],"benchmarks":[77],"meta-evaluation,":[79],"demonstrating":[80],"can":[83],"achieve":[84],"high":[85],"alignment":[86],"with":[87,164],"human":[88],"preferences":[89],"in":[90,104,178],"an":[91],"economical":[92],"manner.":[93],"Additionally,":[94],"we":[95,114,142],"explore":[96],"insights":[97],"into":[98],"LLM-as-a-judge":[100],"paradigm,":[101],"revealing":[102],"nuances":[103],"performance":[105,128],"varied":[108],"effects":[109],"reference":[111],"answers.":[112],"Notably,":[113],"observe":[115],"pure":[117],"knowledge":[118],"distillation":[119],"strong":[121],"LLMs,":[122],"though":[123],"common,":[124],"does":[125],"not":[126],"guarantee":[127],"improvement":[129],"through":[130],"scaling.":[131],"propose":[133],"mitigation":[135],"strategy":[136],"based":[137],"on":[138],"instruction-following":[139],"difficulty.":[140],"Furthermore,":[141],"practical":[144],"guidelines":[145],"covering":[146],"data":[147],"balancing,":[148],"prompt":[149],"customization,":[150],"multi-objective":[151],"training,":[152],"metric":[154],"aggregation.":[155],"aim":[157],"our":[159],"method":[160],"findings,":[162],"along":[163],"fine-tuning":[166],"data,":[167],"benchmarks,":[168],"model":[170],"checkpoints,":[171],"support":[173],"future":[174],"research":[175],"this":[179],"area.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}