{"id":"https://openalex.org/W7165362068","doi":"https://doi.org/10.48550/arxiv.2606.19714","title":"AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing","display_name":"AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165362068","doi":"https://doi.org/10.48550/arxiv.2606.19714"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.19714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19714","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.19714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138994515","display_name":"Zilong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084887779","display_name":"Yi-Ting Hung","orcid":"https://orcid.org/0009-0009-5021-6014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung, Yi-Ting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139023635","display_name":"Weiyi He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Weiyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445621","display_name":"Junxi Zhang","orcid":"https://orcid.org/0000-0001-5318-2045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Junxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139015249","display_name":"Lei Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134798316","display_name":"Chi-Kuang Yeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeh, Chi-Kuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.21789999306201935,"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":0.21789999306201935,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.13619999587535858,"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":0.07670000195503235,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.6549000144004822},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6484000086784363},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5353000164031982},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5246999859809875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267000079154968},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6549000144004822},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6484000086784363},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.19714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19714","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.19714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.19714","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4,47],"increasingly":[5],"used":[6],"as":[7,12,133,141],"judges":[8],"for":[9,29,50,98,120],"open-ended":[10],"generation,":[11],"large-scale":[13],"human":[14,30,53,78,105,121],"evaluation":[15,156],"is":[16,68,80,126,138],"often":[17,35],"expensive":[18],"and":[19,116,153,160],"difficult":[20],"to":[21,84,127],"scale,":[22],"yet":[23],"their":[24],"preferences":[25],"remain":[26],"imperfect":[27],"proxies":[28],"judgment.":[31],"Existing":[32],"auditing":[33,99],"pipelines":[34],"assume":[36],"that":[37,137],"a":[38,110,131,134,146,149,154],"reliable":[39,114],"subset":[40],"of":[41,60],"examples":[42],"or":[43,57],"clean":[44],"supervision":[45],"signals":[46],"available":[48],"beforehand,":[49],"example":[51],"from":[52],"annotation,":[54],"heuristic":[55],"filtering,":[56],"the":[58,70],"outputs":[59],"strong":[61],"judges.":[62],"In":[63],"LLM":[64],"evaluation,":[65],"this":[66],"assumption":[67],"fragile:":[69],"initial":[71],"split":[72],"may":[73],"inherit":[74],"judge":[75,132],"bias,":[76],"while":[77],"verification":[79],"typically":[81],"too":[82],"scarce":[83],"define":[85],"stable":[86,150],"groups":[87],"at":[88],"scale.":[89],"We":[90,144],"propose":[91],"AURA,":[92],"an":[93],"adaptive":[94],"uncertainty--aware":[95],"refinement":[96,151],"framework":[97],"pairwise":[100,162],"LLM--as--a--judge":[101],"decisions":[102],"under":[103],"selected":[104],"verification.":[106],"AURA":[107],"iteratively":[108],"learns":[109],"human-consistency":[111],"signal,":[112],"propagates":[113],"evidence,":[115],"prioritizes":[117],"uncertain":[118],"comparisons":[119],"review.":[122],"The":[123],"key":[124],"idea":[125],"treat":[128],"trust":[129],"in":[130],"latent":[135],"quantity":[136],"progressively":[139],"refined":[140],"evidence":[142],"accumulates.":[143],"provide":[145],"compact":[147],"formulation,":[148],"procedure,":[152],"comprehensive":[155],"on":[157],"both":[158],"synthetic":[159],"real":[161],"LLM-answer":[163],"data.":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-20T00:00:00"}