{"id":"https://openalex.org/W4416034656","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.711","title":"SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone","display_name":"SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034656","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.711"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.711","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.711","pdf_url":"https://aclanthology.org/2025.findings-emnlp.711.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.711.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109481132","display_name":"Nishant Subramani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishant Subramani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Alfredo Gomez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alfredo Gomez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mona T. Diab","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":"13220","last_page":"13233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.050200000405311584,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.050200000405311584,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11195","display_name":"Simulation Techniques and Applications","score":0.023399999365210533,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.020500000566244125,"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/benchmark","display_name":"Benchmark (surveying)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2687000036239624},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26600000262260437},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.257099986076355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5479000210762024},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5059999823570251},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3231000006198883},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.711","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.711","pdf_url":"https://aclanthology.org/2025.findings-emnlp.711.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.711","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.711","pdf_url":"https://aclanthology.org/2025.findings-emnlp.711.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034656.pdf","grobid_xml":"https://content.openalex.org/works/W4416034656.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"language":[1],"models":[2,95,167],"are":[3,9],"evaluated":[4],"on":[5,71,162],"large":[6],"benchmarks,":[7,92],"which":[8,108],"difficult":[10],"to":[11,36,68,78,98],"make":[12],"sense":[13],"of,":[14],"especially":[15],"for":[16,133],"model":[17,51,157,178,183],"selection.Looking":[18],"at":[19,144],"the":[20,65,131],"raw":[21,113],"evaluation":[22,114],"numbers":[23],"themselves":[24],"using":[25,112,148],"a":[26,32,57,72,110,163,199],"model-centric":[27],"lens,":[28],"we":[29,47,55,63,119,139,153],"propose":[30],"SimBA,":[31],"three":[33,40,79,91],"phase":[34],"framework":[35],"Simplify":[37],"Benchmark":[38],"Analysis.The":[39],"phases":[41],"of":[42,75,130,143,166],"SimBA":[43,77,175],"are:":[44],"stalk,":[45],"where":[46,54,62],"conduct":[48],"dataset":[49,186,193],"&":[50],"comparisons,":[52],"prowl,":[53],"discover":[56],"representative":[58,66,104,151],"subset,":[59],"and":[60,85,94,127,136,159,185],"pounce,":[61],"use":[64],"subset":[67],"predict":[69,160],"performance":[70,161],"held-out":[73],"set":[74,105,165],"models.Applying":[76],"popular":[80],"LM":[81],"benchmarks:":[82],"HELM,":[83,134],"MMLU,":[84,135],"BigBenchLite":[86,137],"reveals":[87],"that":[88,121],"across":[89],"all":[90],"datasets":[93,132,197],"relate":[96],"strongly":[97],"one":[99],"another":[100],"(stalk).We":[101],"develop":[102],"an":[103],"discovery":[106],"algorithm":[107],"covers":[109],"benchmark":[111],"scores":[115],"alone.Using":[116],"our":[117],"algorithm,":[118],"find":[120],"with":[122,168],"6.25%":[123],"(1/16),":[124],"1.7%":[125],"(1/58),":[126],"28.4%":[128],"(21/74)":[129],"respectively,":[138],"achieve":[140],"coverage":[141],"levels":[142],"least":[145],"95%":[146],"(prowl).Additionally,":[147],"just":[149],"these":[150],"subsets,":[152],"can":[154,176],"both":[155],"preserve":[156],"ranks":[158],"heldout":[164],"near":[169],"zero":[170],"mean-squared":[171],"error":[172],"(pounce).Taken":[173],"together,":[174],"help":[177],"developers":[179],"improve":[180],"efficiency":[181],"during":[182],"training":[184],"creators":[187],"validate":[188],"whether":[189],"their":[190],"newly":[191],"created":[192],"differs":[194],"from":[195],"existing":[196],"in":[198],"benchmark.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}