{"id":"https://openalex.org/W4413267864","doi":"https://doi.org/10.1145/3696630.3728572","title":"OpsEval: A Comprehensive Benchmark Suite for Evaluating Large Language Models\u2019 Capability in IT Operations Domain","display_name":"OpsEval: A Comprehensive Benchmark Suite for Evaluating Large Language Models\u2019 Capability in IT Operations Domain","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4413267864","doi":"https://doi.org/10.1145/3696630.3728572"},"language":null,"primary_location":{"id":"doi:10.1145/3696630.3728572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728572","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3696630.3728572","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuhe Liu","orcid":"https://orcid.org/0009-0002-0324-7749"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhe Liu","raw_affiliation_strings":["BNRist, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0324-7749","affiliations":[{"raw_affiliation_string":"BNRist, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073273454","display_name":"Changhua Pei","orcid":"https://orcid.org/0000-0001-9288-4787"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhua Pei","raw_affiliation_strings":["Chinese Academy of Sciences, Computer Network Information Center, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9288-4787","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Computer Network Information Center, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779169","display_name":"Longlong Xu","orcid":"https://orcid.org/0009-0008-7364-1307"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longlong Xu","raw_affiliation_strings":["BNRist, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7364-1307","affiliations":[{"raw_affiliation_string":"BNRist, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053848632","display_name":"Bohan Chen","orcid":"https://orcid.org/0009-0002-6804-7473"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Chen","raw_affiliation_strings":["BNRist, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6804-7473","affiliations":[{"raw_affiliation_string":"BNRist, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045587504","display_name":"Mingze Sun","orcid":"https://orcid.org/0000-0002-4205-7182"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingze Sun","raw_affiliation_strings":["BNRist, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4205-7182","affiliations":[{"raw_affiliation_string":"BNRist, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhirui Zhang","orcid":"https://orcid.org/0009-0002-9186-8069"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhirui Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-9186-8069","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027731066","display_name":"Yongqian Sun","orcid":"https://orcid.org/0000-0003-0266-7899"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqian Sun","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0266-7899","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072210083","display_name":"Shenglin Zhang","orcid":"https://orcid.org/0000-0003-0330-0028"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenglin Zhang","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0330-0028","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Wang","orcid":"https://orcid.org/0009-0000-1971-0860"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["BNRist, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1971-0860","affiliations":[{"raw_affiliation_string":"BNRist, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014025074","display_name":"Haiming Zhang","orcid":"https://orcid.org/0000-0001-9351-3320"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiming Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Computer Network Information Center, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9351-3320","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Computer Network Information Center, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372619","display_name":"Jianhui Li","orcid":"https://orcid.org/0009-0001-6253-9808"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhui Li","raw_affiliation_strings":["Chinese Academy of Sciences, Computer Network Information Center, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-6253-9808","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Computer Network Information Center, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030689390","display_name":"Gaogang Xie","orcid":"https://orcid.org/0000-0003-4964-1135"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaogang Xie","raw_affiliation_strings":["Chinese Academy of Sciences, Computer Network Information Center, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4964-1135","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Computer Network Information Center, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xidao Wen","orcid":"https://orcid.org/0009-0002-4202-3748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xidao Wen","raw_affiliation_strings":["BizSeer, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4202-3748","affiliations":[{"raw_affiliation_string":"BizSeer, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101900805","display_name":"Xiaohui Nie","orcid":"https://orcid.org/0000-0002-0371-854X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Nie","raw_affiliation_strings":["Chinese Academy of Sciences, Computer Network Information Center, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0371-854X","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Computer Network Information Center, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070950193","display_name":"Minghua Ma","orcid":"https://orcid.org/0000-0002-6303-1731"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghua Ma","raw_affiliation_strings":["Microsoft, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-6303-1731","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046419834","display_name":"Dan Pei","orcid":"https://orcid.org/0000-0002-5113-838X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Pei","raw_affiliation_strings":["BNRist, Beijing, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5113-838X","affiliations":[{"raw_affiliation_string":"BNRist, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":16,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4323,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9491152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"503","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9241999983787537,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9241999983787537,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/suite","display_name":"Suite","score":0.9076454639434814},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8322963118553162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925634980201721},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.60340815782547},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.432074636220932}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.9076454639434814},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8322963118553162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925634980201721},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.60340815782547},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.432074636220932},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696630.3728572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728572","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696630.3728572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696630.3728572","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1652589396","display_name":null,"funder_award_id":"2024YFB4505903","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4202455740","display_name":null,"funder_award_id":"XXX-63253249","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4440372660","display_name":null,"funder_award_id":"62202445","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5602403601","display_name":null,"funder_award_id":"62302244","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8260126168","display_name":null,"funder_award_id":"62272249","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4385572697","https://openalex.org/W4386721326"],"related_works":["https://openalex.org/W4379115841","https://openalex.org/W2083794993","https://openalex.org/W1511772879","https://openalex.org/W4394660363","https://openalex.org/W2186315912","https://openalex.org/W2588591308","https://openalex.org/W2248125223","https://openalex.org/W2910542634","https://openalex.org/W2127898439","https://openalex.org/W3082894236"],"abstract_inverted_index":{"In":[0],"recent":[1],"decades,":[2],"the":[3,10,30,92,119,137,142,187,261],"field":[4],"of":[5,13,35,69,72,79,88,121,186,203,242],"software":[6],"engineering":[7,104],"has":[8,40,239],"driven":[9],"rapid":[11],"evolution":[12],"Information":[14],"Technology":[15],"(IT)":[16],"systems,":[17,95],"including":[18,152],"advances":[19],"in":[20,55,62,84,141,193,200,236],"cloud":[21],"computing,":[22],"5G":[23],"networks,":[24],"and":[25,33,74,77,109,127,161,175,183,218,247,252,257,267],"financial":[26],"information":[27],"platforms.":[28],"Ensuring":[29],"stability,":[31],"reliability,":[32],"robustness":[34],"these":[36],"complex":[37],"IT":[38,94],"systems":[39],"emerged":[41],"as":[42,65,215],"a":[43,147,162,240],"critical":[44],"challenge.":[45],"Large":[46],"language":[47],"models":[48],"(LLMs)":[49],"that":[50],"have":[51,180,269],"exhibited":[52],"remarkable":[53],"capabilities":[54],"NLP-related":[56,114],"tasks":[57],"are":[58],"showing":[59],"great":[60],"potential":[61],"AIOps,":[63],"such":[64,214],"root":[66],"cause":[67],"analysis":[68],"failures,":[70],"generation":[71],"operations":[73],"maintenance":[75],"scripts,":[76],"summarizing":[78],"alert":[80],"information.":[81],"Unlike":[82],"knowledge":[83,87],"general":[85],"corpora,":[86],"Ops":[89,125,143,158,165],"varies":[90],"with":[91,244],"different":[93],"encompassing":[96],"various":[97,107,194,212],"private":[98],"sub-domain":[99],"knowledge,":[100],"sensitive":[101],"to":[102,106,196,226,255],"prompt":[103],"due":[105],"sub-domains,":[108],"containing":[110],"numerous":[111],"terminologies.":[112],"Existing":[113],"benchmarks":[115],"can":[116,133],"not":[117,134],"guide":[118],"selection":[120],"suitable":[122],"LLMs":[123,210,225],"for":[124,234],"(OpsLLM),":[126],"current":[128,198],"metrics":[129],"(e.g.,":[130],"BLEU,":[131],"ROUGE)":[132],"adequately":[135],"reflect":[136],"question-answering":[138],"(QA)":[139],"effectiveness":[140],"domain.":[144],"We":[145,179,205,228],"propose":[146,230],"comprehensive":[148],"benchmark":[149],"suite,":[150],"OpsEval,":[151],"an":[153,157,231],"Ops-oriented":[154],"evaluation":[155,159,167,232],"dataset,":[156],"benchmark,":[160],"specially":[163],"designed":[164],"QA":[166,177,235],"method.":[168],"Our":[169],"dataset":[170,188,266],"contains":[171],"7,334":[172],"multiple-choice":[173],"questions":[174],"1,736":[176],"questions.":[178],"carefully":[181],"selected":[182],"released":[184],"20%":[185],"written":[189],"by":[190,250],"domain":[191],"experts":[192,246],"sub-domains":[195],"assist":[197],"researchers":[199],"preliminary":[201],"evaluations":[202],"OpsLLMs1.":[204],"test":[206],"over":[207],"24":[208],"latest":[209],"under":[211],"settings":[213],"self-consistency,":[216],"chain-of-thought,":[217],"in-context":[219],"learning,":[220],"revealing":[221],"findings":[222],"when":[223],"applying":[224],"Ops.":[227],"also":[229],"method":[233],"Ops,":[237],"which":[238],"coefficient":[241],"0.9185":[243],"human":[245],"is":[248],"improved":[249],"0.4471":[251],"1.366":[253],"compared":[254],"BLEU":[256],"ROUGE,":[258],"respectively.":[259],"Over":[260],"past":[262],"one":[263],"year,":[264],"our":[265],"leaderboard":[268],"been":[270],"continuously":[271],"updated.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-08-18T00:00:00"}
