{"id":"https://openalex.org/W4415665495","doi":"https://doi.org/10.1145/3763000","title":"An Improved Autoregressive Evaluation Paradigm for Large Language Models","display_name":"An Improved Autoregressive Evaluation Paradigm for Large Language Models","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4415665495","doi":"https://doi.org/10.1145/3763000"},"language":"en","primary_location":{"id":"doi:10.1145/3763000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3763000","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100622779","display_name":"Jipeng Zhang","orcid":"https://orcid.org/0000-0002-3269-6992"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jipeng Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-3269-6992","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085173469","display_name":"Rui Pan","orcid":"https://orcid.org/0000-0001-7217-0656"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rui Pan","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0001-7217-0656","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuzheng Hu","orcid":"https://orcid.org/0009-0008-7313-6108"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzheng Hu","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, Illinois, USA","University of Illinois Urbana-Champaign, USA"],"raw_orcid":"https://orcid.org/0009-0008-7313-6108","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036359845","display_name":"KaShun Shum","orcid":"https://orcid.org/0009-0006-5168-8345"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"KaShun Shum","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0009-0006-5168-8345","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004714781","display_name":"Guanyu Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanyu Yao","raw_affiliation_strings":["University of California Santa Barbara, Santa Barbara, California, USA","University of California, Santa Barbara, USA"],"raw_orcid":"https://orcid.org/0009-0004-8642-3860","affiliations":[{"raw_affiliation_string":"University of California Santa Barbara, Santa Barbara, California, USA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109152867","display_name":"Xiang Liu","orcid":"https://orcid.org/0009-0003-2639-1804"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0009-0003-2639-1804","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084438237","display_name":"Renjie Pi","orcid":"https://orcid.org/0000-0002-5033-7096"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renjie Pi","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-5033-7096","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061778641","display_name":"Hanze Dong","orcid":"https://orcid.org/0000-0002-8846-1260"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hanze Dong","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-8846-1260","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058966093","display_name":"Shizhe Diao","orcid":"https://orcid.org/0000-0002-3325-9209"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shizhe Diao","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-3325-9209","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102080959","display_name":"Yong Lin","orcid":"https://orcid.org/0000-0003-3525-6738"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yong Lin","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","The Hong Kong University of Science and Technology, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0003-3525-6738","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101198967","display_name":"Han Zhao","orcid":"https://orcid.org/0000-0002-8579-1600"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Zhao","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, Illinois, USA","University of Illinois Urbana-Champaign, USA"],"raw_orcid":"https://orcid.org/0000-0002-8579-1600","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, Illinois, USA","University of Illinois Urbana-Champaign, Urbana, Illinois, United States"],"raw_orcid":"https://orcid.org/0000-0002-5511-2558","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, Illinois, United States","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1972389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"4","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.8808000087738037,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.8808000087738037,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.01640000008046627,"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":0.015599999576807022,"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/perplexity","display_name":"Perplexity","score":0.8467000126838684},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7293999791145325},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7289999723434448},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4198000133037567},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.3995000123977661}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8467000126838684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835099995136261},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7293999791145325},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7289999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5471000075340271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5292999744415283},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C101601086","wikidata":"https://www.wikidata.org/wiki/Q3753228","display_name":"Rank correlation","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3763000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3763000","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-166826","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-166826","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1985153860","https://openalex.org/W2045563097","https://openalex.org/W2050138804","https://openalex.org/W2069870183","https://openalex.org/W2101105183","https://openalex.org/W2343954916","https://openalex.org/W2799544270","https://openalex.org/W2912924812","https://openalex.org/W2963339397","https://openalex.org/W2997200074","https://openalex.org/W2998617917","https://openalex.org/W3194676777","https://openalex.org/W3212496002","https://openalex.org/W4229005866","https://openalex.org/W4308760226","https://openalex.org/W4320005767","https://openalex.org/W4322718191","https://openalex.org/W4362655426"],"related_works":[],"abstract_inverted_index":{"The":[0,32],"AI":[1],"community":[2],"has":[3,114],"witnessed":[4],"the":[5,15,44,82,90,94,119,129,143,146,152,177],"emergence":[6],"of":[7,17,58,122,132,145,179],"various":[8],"chat-style":[9],"Large":[10],"Language":[11],"Models":[12],"(LLMs)":[13],"since":[14],"advent":[16],"ChatGPT.":[18],"Despite":[19],"significant":[20],"progress":[21,121],"in":[22,117,161,197],"this":[23,158,162],"area,":[24],"evaluating":[25],"these":[26],"models":[27,63,134],"remains":[28,97],"a":[29,56,74,78,140,166],"substantial":[30],"challenge.":[31],"evaluations":[33],"provided":[34],"by":[35],"humans":[36],"or":[37],"GPT-4":[38,214],"oracles":[39],"are":[40,49,110],"often":[41,69],"taken":[42],"as":[43,104],"gold":[45],"standard,":[46],"but":[47],"they":[48,68,125],"neither":[50],"automatic":[51],"nor":[52],"scalable.":[53],"More":[54],"recently,":[55],"series":[57],"(open":[59],"source)":[60],"LLM-based":[61],"judge":[62,76],"have":[64],"been":[65],"introduced,":[66],"yet":[67],"exhibit":[70],"model-specific":[71],"biases,":[72],"e.g.,":[73],"LLaMA-family":[75,79],"favors":[77],"model.":[80],"On":[81],"other":[83],"hand,":[84],"autoregressive":[85,168],"evaluation":[86,178],"metrics,":[87],"which":[88],"holds":[89],"potential":[91],"to":[92,127,136,175],"address":[93,157],"aforementioned":[95],"issues,":[96],"underexplored.":[98],"Among":[99],"them,":[100],"likelihood-based":[101,190],"metrics":[102],"such":[103],"perplexity":[105],"and":[106,113,200,209],"Negative":[107],"Log-Likelihood":[108],"(NLL)":[109],"widely":[111],"adopted":[112],"proven":[115],"effective":[116],"tracking":[118],"pre-training":[120],"LLMs.":[123,181],"However,":[124],"struggle":[126],"evaluate":[128],"generation":[130],"capabilities":[131],"fine-tuned":[133,180],"due":[135],"exposure":[137],"bias":[138],",":[139],"phenomenon":[141],"where":[142],"distribution":[144],"model\u2019s":[147],"output":[148],"gradually":[149],"deviates":[150],"from":[151],"ground-truth":[153],"during":[154],"inference.":[155],"To":[156],"key":[159],"issue,":[160],"article,":[163],"we":[164],"propose":[165],"novel":[167],"metric,":[169],"Normalized":[170],"Discounted":[171],"Cumulative":[172],"Gain":[173],"(NDCG),":[174],"improve":[176],"Our":[182],"experimental":[183],"results":[184],"demonstrate":[185],"that":[186],"NDCG":[187],"significantly":[188],"outperforms":[189],"metrics:":[191],"it":[192],"shows":[193],"over":[194],"45%":[195],"improvement":[196],"both":[198],"Spearman":[199],"Kendall\u2019s":[201],"tau":[202],"correlation":[203],"coefficients":[204],"for":[205,217],"commonsense":[206],"QA":[207],"tasks,":[208],"aligns":[210],"more":[211],"closely":[212],"with":[213],"Elo":[215],"rankings":[216],"instruction-tuned":[218],"models.":[219]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-29T00:00:00"}
