{"id":"https://openalex.org/W7129012486","doi":"https://doi.org/10.48550/arxiv.2602.13110","title":"SCOPE: Selective Conformal Optimized Pairwise LLM Judging","display_name":"SCOPE: Selective Conformal Optimized Pairwise LLM Judging","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129012486","doi":"https://doi.org/10.48550/arxiv.2602.13110"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.13110","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.13110","pdf_url":"https://arxiv.org/pdf/2602.13110","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.13110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042267620","display_name":"Sher Badshah","orcid":"https://orcid.org/0000-0001-6780-3746","observed_orcids":["https://orcid.org/0000-0001-6780-3746"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Badshah, Sher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009083947","display_name":"Ali Emami","orcid":"https://orcid.org/0000-0002-3513-9497","observed_orcids":["https://orcid.org/0000-0002-3513-9497"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emami, Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126156673","display_name":"Hassan Sajjad","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sajjad, Hassan","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":true,"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":0.1851000040769577,"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":0.1851000040769577,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09809999912977219,"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":0.06889999657869339,"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/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.6769999861717224},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.8840000033378601},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.6079999804496765},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"false discovery rate","score":0.6970000267028809},{"id":"https://openalex.org/keywords/exchangeability","display_name":"exchangeability","score":0.5960000157356262},{"id":"https://openalex.org/keywords/llm-based-evaluation","display_name":"LLM-based evaluation","score":0.49900001287460327}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.861299991607666},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.7714999914169312},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5365999937057495},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C2780839233","wikidata":"https://www.wikidata.org/wiki/Q16000284","display_name":"Pairwise error probability","level":4,"score":0.34940001368522644},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.305400013923645},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2980000078678131},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.13110","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.13110","pdf_url":"https://arxiv.org/pdf/2602.13110","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.13110","doi":"https://doi.org/10.48550/arxiv.2602.13110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13110","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":"pmh:oai:arXiv.org:2602.13110","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.13110","pdf_url":"https://arxiv.org/pdf/2602.13110","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320330759","display_name":"Research Nova Scotia","ror":"https://ror.org/00x5ftp92"},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7129012486.pdf","grobid_xml":"https://content.openalex.org/works/W7129012486.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7212924736","https://openalex.org/W7221749767","https://openalex.org/W7167215375","https://openalex.org/W4416785361","https://openalex.org/W7220134105","https://openalex.org/W4412945123","https://openalex.org/W4414790729","https://openalex.org/W7108335764","https://openalex.org/W7160932656","https://openalex.org/W7134841483"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6],"as":[7],"scalable":[8],"judges":[9],"in":[10,95],"pairwise":[11,87],"evaluation,":[12],"but":[13],"they":[14],"remain":[15],"prone":[16],"to":[17,118,124],"miscalibration":[18],"and":[19,75,97,113,138],"biases.":[20],"We":[21],"propose":[22],"\\textsc{Scope}":[23,55,100,121],"(Selective":[24],"Conformal":[25],"Optimized":[26],"Pairwise":[27],"Evaluation),":[28],"a":[29,49,57],"framework":[30],"that":[31,134],"calibrates":[32],"an":[33,82],"acceptance":[34],"threshold":[35],"so":[36],"that,":[37],"under":[38,71,128],"exchangeability,":[39],"the":[40,69,77,103,129],"error":[41],"rate":[42],"among":[43],"non-abstained":[44],"judgments":[45,127],"is":[46],"at":[47,111],"most":[48],"user-specified":[50],"level":[51],"$\u03b1$.":[52],"To":[53],"supply":[54],"with":[56],"bias-neutral":[58],"uncertainty":[59],"signal,":[60],"we":[61],"introduce":[62],"Bidirectional":[63],"Preference":[64],"Entropy":[65],"(BPE),":[66],"which":[67],"queries":[68],"judge":[70],"both":[72],"response":[73],"positions":[74],"converts":[76],"order-averaged":[78],"preference":[79],"probability":[80],"into":[81],"entropy-based":[83],"score.":[84],"Across":[85],"various":[86],"judging":[88],"benchmarks,":[89],"BPE":[90,135],"outperforms":[91],"standard":[92],"confidence":[93],"proxies":[94],"calibration":[96],"discrimination,":[98],"while":[99],"consistently":[101],"satisfies":[102],"target":[104],"risk":[105,131],"bound":[106],"(empirical":[107],"FDR":[108],"$\\approx":[109],"0.097$--$0.099$":[110],"$\u03b1=0.10$)":[112],"retains":[114],"substantial":[115],"coverage.":[116],"Compared":[117],"vanilla":[119],"baselines,":[120],"accepts":[122],"up":[123],"$2.4\\times$":[125],"more":[126],"same":[130],"constraint,":[132],"demonstrating":[133],"enables":[136],"reliable":[137],"high-coverage":[139],"LLM-based":[140],"evaluation.":[141]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-17T00:00:00"}