{"id":"https://openalex.org/W7220934952","doi":"https://doi.org/10.18653/2026.findings-emnlp.1661","title":"Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions","display_name":"Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7220934952","doi":"https://doi.org/10.18653/2026.findings-emnlp.1661"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1661","doi":"https://doi.org/10.18653/2026.findings-emnlp.1661","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1661","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1661.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.1661.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157888058","display_name":"Wenqi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenqi Li","raw_affiliation_strings":["University at Albany , State University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Albany , State University of New York","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157984594","display_name":"Bin Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["West Virginia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"West Virginia University","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065533387","display_name":"Mindi Ruan","orcid":"https://orcid.org/0000-0002-7931-500X","observed_orcids":["https://orcid.org/0000-0002-7931-500X"]},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mindi Ruan","raw_affiliation_strings":["West Virginia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"West Virginia University","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122638016","display_name":"Chuanbo Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuanbo Hu","raw_affiliation_strings":["University at Albany , State University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Albany , State University of New York","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157897291","display_name":"Minglei Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minglei Yin","raw_affiliation_strings":["University at Albany , State University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Albany , State University of New York","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157920984","display_name":"Xin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["University at Albany , State University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Albany , State University of New York","institution_ids":["https://openalex.org/I392282"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.68142713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35408","last_page":"35427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6190999746322632,"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":0.6190999746322632,"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":0.09139999747276306,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.05339999869465828,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.8669999837875366},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.670199990272522},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6626999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459000110626221},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5512999892234802},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C101601086","wikidata":"https://www.wikidata.org/wiki/Q3753228","display_name":"Rank correlation","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1661","doi":"https://doi.org/10.18653/2026.findings-emnlp.1661","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1661","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1661.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2610.09229","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09229","pdf_url":"https://arxiv.org/pdf/2610.09229","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.09229","doi":"https://doi.org/10.48550/arxiv.2610.09229","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09229","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.1661","doi":"https://doi.org/10.18653/2026.findings-emnlp.1661","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1661","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1661.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1401278678","display_name":"HCC: Small: Toward Computational Modeling of Autism Spectrum Disorder: Multimodal Data Collection, Fusion, and Phenotyping","funder_award_id":"2401748","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332911","display_name":"University at Albany","ror":"https://ror.org/012zs8222"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220934952.pdf","grobid_xml":"https://content.openalex.org/works/W7220934952.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3210904070","https://openalex.org/W4416785361"],"related_works":["https://openalex.org/W7214756950","https://openalex.org/W7114820736","https://openalex.org/W7134036278","https://openalex.org/W7212924736","https://openalex.org/W7090848549","https://openalex.org/W7165368332","https://openalex.org/W4403583114","https://openalex.org/W7165611736","https://openalex.org/W7214926339","https://openalex.org/W7162309258"],"abstract_inverted_index":{"LLM-as-judge":[0],"is":[1,12,59,143,161],"now":[2],"a":[3,17,29,39,67,100,188],"standard":[4],"tool":[5],"for":[6,195],"scalable":[7],"evaluation,":[8],"but":[9,160],"judge":[10,30],"performance":[11],"still":[13],"often":[14],"summarized":[15],"by":[16,114,137,146,184],"single":[18],"accuracy":[19,47,172,194],"number.This":[20],"aggregate":[21,115,147,193],"view":[22],"hides":[23],"the":[24,70,122,132,153,169,175,179],"deployment":[25],"conditions":[26,50],"under":[27,164],"which":[28],"succeeds":[31],"or":[32,77],"fails.We":[33],"introduce":[34],"Conditional":[35],"Accuracy":[36],"Profiling":[37],"(CAP),":[38],"post-hoc":[40],"diagnostic":[41],"framework":[42],"that":[43],"decomposes":[44],"pairwise":[45,95],"LLM-judge":[46],"into":[48,52],"eight":[49,108],"organized":[51],"content":[53],"sensitivity,":[54],"robustness,":[55],"and":[56],"rationale":[57],"quality.CAP":[58],"benchmark-agnostic:":[60],"it":[61],"can":[62,84],"be":[63,85],"applied":[64],"directly":[65],"when":[66,81],"benchmark":[68],"provides":[69],"required":[71],"annotations,":[72],"approximately":[73],"through":[74,78],"task-subset":[75],"proxies,":[76],"controlled":[79,101],"augmentation":[80],"perturbation":[82],"pairs":[83],"generated.We":[86],"instantiate":[87],"CAP":[88],"on":[89,117],"seven":[90,136],"LLM":[91,197],"judges":[92,124],"across":[93],"six":[94],"judging":[96],"benchmarks,":[97,149],"including":[98],"JUDGEREVA-STANDARD,":[99],"testbed":[102],"we":[103],"created":[104],"to":[105,127],"support":[106],"all":[107],"conditions.CAP":[109],"exposes":[110],"profile":[111],"differences":[112],"hidden":[113],"accuracy:":[116],"JUDGEREVA's":[118],"judge-independent":[119],"Hard-Constructed":[120],"subset,":[121],"two":[123],"most":[125],"sensitive":[126],"omitted":[128],"qualifications":[129],"rank":[130,155],"in":[131],"bottom":[133],"three":[134],"of":[135],"overall":[138],"accuracy,":[139],"so":[140],"omission":[141],"sensitivity":[142],"not":[144],"predicted":[145],"accuracy.Across":[148],"Position":[150],"Robustness":[151],"shows":[152],"strongest":[154],"stability":[156],"(mean":[157],"Spearman":[158],"\u03c1=0.87)":[159],"itself":[162],"fragile":[163],"JudgeBench-Pro":[165],"adversarial":[166],"stress,":[167],"showing":[168],"largest":[170],"mean":[171],"drop":[173],"among":[174],"shared":[176],"conditions,":[177],"though":[178],"dominant":[180],"degradation":[181],"channel":[182],"varies":[183],"judge.Condition-level":[185],"profiles":[186],"provide":[187],"more":[189],"actionable":[190],"basis":[191],"than":[192],"selecting":[196],"judges.":[198]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-09T00:00:00"}