{"id":"https://openalex.org/W4416036140","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1051","title":"Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models","display_name":"Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036140","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1051"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1051","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1051","pdf_url":"https://aclanthology.org/2025.emnlp-main.1051.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1051.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048597650","display_name":"Hyeonseok Moon","orcid":"https://orcid.org/0000-0002-0841-4262"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":true,"raw_author_name":"Hyeonseok Moon","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I4210161052","https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003302699","display_name":"Seongtae Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Seongtae Hong","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I4210161052","https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014883878","display_name":"Jaehyung Seo","orcid":"https://orcid.org/0000-0002-4761-9818"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Jaehyung Seo","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I4210161052","https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033580486","display_name":"Heuiseok Lim","orcid":"https://orcid.org/0000-0002-9269-1157"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Heuiseok Lim","raw_affiliation_strings":["Department of Computer Science and Engineering , Korea University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I4210161052","https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048597650"],"corresponding_institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17484743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20820","last_page":"20834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3183000087738037,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.3183000087738037,"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/T10028","display_name":"Topic Modeling","score":0.13760000467300415,"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/T13629","display_name":"Text Readability and Simplification","score":0.10750000178813934,"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/metric","display_name":"Metric (unit)","score":0.6187000274658203},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5353000164031982},{"id":"https://openalex.org/keywords/metric-system","display_name":"Metric system","score":0.3393000066280365},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3346000015735626},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27459999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589000225067139},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421099990606308},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C193429382","wikidata":"https://www.wikidata.org/wiki/Q232405","display_name":"Metric system","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1051","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1051","pdf_url":"https://aclanthology.org/2025.emnlp-main.1051.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1051","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1051","pdf_url":"https://aclanthology.org/2025.emnlp-main.1051.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1630947553","display_name":null,"funder_award_id":"RS-2022-II220369","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3996153573","display_name":null,"funder_award_id":"RS-2022-II220369","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7542792045","display_name":null,"funder_award_id":"IITP-2025-RS-2020-II201819","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036140.pdf","grobid_xml":"https://content.openalex.org/works/W4416036140.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"frontier-level":[1],"LLMs":[2,37,73],"have":[3],"saturated":[4],"many":[5],"previously":[6],"difficult":[7],"benchmarks,":[8],"leaving":[9],"little":[10],"room":[11],"for":[12,19,140],"further":[13],"differentiation.This":[14],"progress":[15],"highlights":[16],"the":[17,106,122,142],"need":[18],"challenging":[20],"benchmarks":[21,49],"that":[22,50,103,131],"provide":[23,98,111],"objective":[24,92,138],"verification.In":[25],"this":[26],"paper,":[27],"we":[28,97],"introduce":[29],"MCBench,":[30],"a":[31,99],"benchmark":[32,117],"designed":[33,119],"to":[34,69,120],"evaluate":[35,105],"whether":[36,72],"can":[38,74,104],"execute":[39],"string-matching":[40],"NLP":[41],"metrics":[42,114],"by":[43],"strictly":[44],"following":[45],"step-by-step":[46,77],"instructions.Unlike":[47],"prior":[48],"depend":[51],"on":[52],"subjective":[53],"judgments":[54],"or":[55],"general":[56],"reasoning,":[57],"MCBench":[58,132],"offers":[59],"an":[60,135],"objective,":[61],"deterministic":[62],"and":[63,84,115,137],"codeverifiable":[64],"evaluation.This":[65],"setup":[66],"allows":[67],"us":[68],"systematically":[70],"test":[71],"maintain":[75],"accurate":[76],"execution,":[78],"including":[79],"instruction":[80,124],"adherence,":[81],"numerical":[82],"computation,":[83],"long-range":[85],"consistency":[86],"in":[87],"handling":[88],"intermediate":[89],"results.To":[90],"ensure":[91],"evaluation":[93],"of":[94,108,127,144],"these":[95],"abilities,":[96],"parallel":[100],"reference":[101],"code":[102],"accuracy":[107],"LLM":[109],"output.We":[110],"three":[112,116],"evaluative":[113],"variants":[118],"measure":[121],"detailed":[123],"understanding":[125],"capability":[126],"LLMs.Our":[128],"analyses":[129],"show":[130],"serves":[133],"as":[134],"effective":[136],"tool":[139],"evaluating":[141],"capabilities":[143],"cuttingedge":[145],"LLMs.":[146]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}