{"id":"https://openalex.org/W7139101371","doi":"https://doi.org/10.1609/aaai.v40i47.41427","title":"PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking Estimation","display_name":"PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking Estimation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7139101371","doi":"https://doi.org/10.1609/aaai.v40i47.41427"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i47.41427","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i47.41427","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41427/45388","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41427/45388","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123992815","display_name":"Abhishek Divekar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Abhishek Divekar","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130059522","display_name":"Anirban Majumder","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anirban Majumder","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5123992815"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63082437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"47","first_page":"39929","last_page":"39938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8235999941825867,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8235999941825867,"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":0.05779999867081642,"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":0.04520000144839287,"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/ranking","display_name":"Ranking (information retrieval)","score":0.708299994468689},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6705999970436096},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6682000160217285},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6449999809265137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5878000259399414},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.517799973487854},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3919000029563904},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.3919000029563904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289000153541565},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.708299994468689},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6705999970436096},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6682000160217285},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6449999809265137},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5152000188827515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.490200012922287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46860000491142273},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3919000029563904},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.2750999927520752},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25040000677108765},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i47.41427","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i47.41427","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41427/45388","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i47.41427","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i47.41427","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/41427/45388","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7139101371.pdf","grobid_xml":"https://content.openalex.org/works/W7139101371.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"the":[1,22,116,121,126,153,158],"quality":[2],"of":[3,11,24,66,101,140,155],"search":[4],"systems":[5,19],"traditionally":[6],"requires":[7,74],"a":[8,47],"significant":[9],"number":[10],"human":[12,57],"relevance":[13,102],"annotations.":[14,71],"In":[15],"recent":[16],"times,":[17],"several":[18],"have":[20],"explored":[21],"usage":[23],"Large":[25],"Language":[26],"Models":[27],"(LLMs)":[28],"as":[29,75,77],"automated":[30],"judges":[31],"for":[32,42,99,104,157,165],"this":[33],"task":[34],"while":[35,162],"their":[36],"inherent":[37],"biases":[38],"prevent":[39],"direct":[40],"use":[41],"metric":[43],"estimation.":[44],"We":[45,93],"present":[46],"statistical":[48],"framework":[49,97],"extending":[50,110],"Prediction-Powered":[51],"Inference":[52],"(PPI)":[53],"that":[54,149],"combines":[55],"minimal":[56],"annotations":[58,114],"with":[59],"LLM":[60,166],"judgments":[61],"to":[62,90,112,131],"produce":[63],"reliable":[64],"estimates":[65,156],"metrics":[67],"which":[68],"require":[69],"sub-instance":[70,113],"Our":[72],"method":[73,151],"few":[76],"100":[78],"human-annotated":[79],"queries":[80],"and":[81],"10,000":[82],"unlabeled":[83],"examples,":[84],"reducing":[85],"annotation":[86],"requirements":[87],"significantly":[88],"compared":[89],"traditional":[91],"approaches.":[92],"formulate":[94],"our":[95,150],"proposed":[96],"(PRECISE)":[98],"inference":[100],"uplift":[103],"an":[105],"LLM-based":[106],"query":[107],"reformulation":[108],"application,":[109],"PPI":[111],"at":[115],"query-document":[117],"level.":[118],"By":[119],"reformulating":[120],"metric-integration":[122],"space,":[123],"we":[124],"reduced":[125],"computational":[127],"complexity":[128],"from":[129],"O(2^|C|)":[130],"O(2^K),":[132],"where":[133],"|C|":[134],"represents":[135],"corpus":[136],"size":[137],"(in":[138],"order":[139],"millions).":[141],"Detailed":[142],"experiments":[143],"across":[144],"prominent":[145],"retrieval":[146],"datasets":[147],"demonstrate":[148],"reduces":[152],"variance":[154],"business-critical":[159],"Precision@K":[160],"metric,":[161],"effectively":[163],"correcting":[164],"bias":[167],"in":[168],"low-resource":[169],"settings.":[170]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-20T00:00:00"}