{"id":"https://openalex.org/W7108749436","doi":"https://doi.org/10.5281/zenodo.17811400","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","display_name":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108749436","doi":"https://doi.org/10.5281/zenodo.17811400"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811400","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811400","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yinghao MA","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghao MA","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Siyou Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Juntao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juntao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Emmanouil Benetos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Akira Maezawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akira Maezawa","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54214218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10788","display_name":"Neuroscience and Music Perception","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/comparability","display_name":"Comparability","score":0.7425000071525574},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6794000267982483},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5665000081062317},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.4957999885082245},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4765999913215637},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4410000145435333}],"concepts":[{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.7425000071525574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249000072479248},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6794000267982483},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4765999913215637},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3653999865055084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35120001435279846},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.3019999861717224},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2849999964237213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811400","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811400","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811400","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811400","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.49935150146484375,"id":"https://metadata.un.org/sdg/5"},{"display_name":"Quality Education","score":0.48782065510749817,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,22,114,180,196],"audio-text":[3,66],"large":[4],"language":[5],"models":[6,179],"(LLMs)":[7],"have":[8],"opened":[9],"new":[10],"possibilities":[11],"for":[12,189],"music":[13,40,59,73,103,105,191],"understanding":[14],"and":[15,54,107,161,169,175],"generation.":[16],"However,":[17],"existing":[18],"benchmarks":[19],"are":[20],"limited":[21],"scope,":[23],"often":[24],"relying":[25],"on":[26,68],"simplified":[27],"tasks":[28],"or":[29],"multi-choice":[30],"evaluations":[31],"that":[32],"fail":[33],"to":[34,64],"reflect":[35],"the":[36,173],"complexity":[37],"of":[38,47,72,177],"real-world":[39],"analysis.":[41],"We":[42,137],"reinterpret":[43],"a":[44,57,69,186],"broad":[45],"range":[46],"traditional":[48],"MIR":[49,115,129,182],"annotations":[50],"as":[51],"instruction-following":[52],"formats":[53],"introduce":[55],"CMI-Bench,":[56],"comprehensive":[58],"instruction":[60,192],"following":[61],"benchmark":[62],"designed":[63],"evaluate":[65],"LLMs":[67,160],"diverse":[70],"set":[71],"information":[74],"retrieval":[75],"(MIR)":[76],"tasks.":[77,183],"These":[78],"include":[79],"genre":[80],"classification,":[81,87],"emotion":[82,84],"regression,":[83],"tagging,":[85,104],"instrument":[86,99],"pitch":[88],"estimation,":[89],"key":[90],"detection,":[91,102],"lyrics":[92],"transcription,":[93],"melody":[94],"extraction,":[95],"vocal":[96],"technique":[97,101],"recognition,":[98],"performance":[100,157],"captioning,":[106],"(down)beat":[108],"tracking":[109],"\u2014":[110],"reflecting":[111],"core":[112],"challenges":[113],"research.":[116],"Unlike":[117],"previous":[118,127],"benchmarks,":[119],"CMI-Bench":[120,184],"adopts":[121],"standardized":[122],"evaluation":[123,140],"metrics":[124],"consistent":[125],"with":[126,134,165],"state-of-the-art":[128],"models,":[130,163],"ensuring":[131],"direct":[132],"comparability":[133],"supervised":[135,162],"approaches.":[136],"provide":[138],"an":[139],"toolkit":[141],"supporting":[142],"all":[143],"open-source":[144],"audio-textual":[145],"LLMs,":[146],"including":[147],"LTU,":[148],"Qwen-audio,":[149],"SALMONN,":[150],"MusiLingo,":[151],"etc.":[152],"Experiment":[153],"results":[154],"reveal":[155],"significant":[156],"gaps":[158],"between":[159],"along":[164],"their":[166],"culture,":[167],"chronological":[168],"gender":[170],"bias,":[171],"highlighting":[172],"potential":[174],"limitations":[176],"current":[178],"addressing":[181],"establishes":[185],"unified":[187],"foundation":[188],"evaluating":[190],"following,":[193],"driving":[194],"progress":[195],"music-aware":[197],"LLMs.":[198]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}