{"id":"https://openalex.org/W6893219887","doi":"https://doi.org/10.5281/zenodo.14877281","title":"Can LLMs \"Reason\" in Music? an Evaluation of LLMs' Capability of Music Understanding and Generation","display_name":"Can LLMs \"Reason\" in Music? an Evaluation of LLMs' Capability of Music Understanding and Generation","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6893219887","doi":"https://doi.org/10.5281/zenodo.14877281"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877281","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877281","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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877281","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ziya Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ziya Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhang Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyue Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyue Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyue Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruibin Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruibin Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yinghao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghao Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Wang","raw_affiliation_strings":[],"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":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yike Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yike Guo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"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":0.37557554,"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":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.24079999327659607,"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":0.24079999327659607,"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":0.13179999589920044,"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/T10028","display_name":"Topic Modeling","score":0.09719999879598618,"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/bridging","display_name":"Bridging (networking)","score":0.621999979019165},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5335000157356262},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.517300009727478},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45179998874664307},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41260001063346863}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4154999852180481},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40459999442100525},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3147999942302704},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.25130000710487366},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25119999051094055},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877281","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877281","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":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877281","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877281","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":""},"sustainable_development_goals":[{"score":0.4644228518009186,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Symbolic":[0],"Music,":[1],"akin":[2],"to":[3,27,105,154],"language,":[4],"can":[5],"be":[6],"encoded":[7],"in":[8,65,85,97],"discrete":[9],"symbols.":[10],"Recent":[11],"research":[12,38,141],"has":[13],"extended":[14],"the":[15,28,40,56,66,147,156],"application":[16],"of":[17,42,80,117],"large":[18],"language":[19],"models":[20],"(LLMs)":[21],"such":[22],"as":[23],"GPT-4":[24],"and":[25,34,51,69,83,102,124,139,152],"Llama2":[26],"symbolic":[29,86],"music":[30,49,87,100,108,150],"domain":[31],"including":[32],"understanding":[33,50],"generation.":[35],"Yet":[36],"scant":[37],"explores":[39],"details":[41],"how":[43],"these":[44],"LLMs":[45,93],"perform":[46],"on":[47,145],"advanced":[48,130],"conditioned":[52],"generation,":[53],"especially":[54],"from":[55],"multi-step":[57,99],"reasoning":[58],"perspective,":[59],"which":[60],"is":[61,133],"a":[62,77],"critical":[63],"aspect":[64],"conditioned,":[67],"editable,":[68],"interactive":[70],"human-computer":[71],"co-creation":[72,157],"process.":[73],"This":[74],"study":[75],"conducts":[76],"thorough":[78],"investigation":[79],"LLMs'":[81,118],"capability":[82,132],"limitations":[84],"processing.":[88],"We":[89],"identify":[90],"that":[91],"current":[92],"exhibit":[94],"poor":[95],"performance":[96],"song-level":[98],"reasoning,":[101,153],"typically":[103],"fail":[104],"leverage":[106],"learned":[107],"knowledge":[109,151],"when":[110],"addressing":[111],"complex":[112],"musical":[113,131],"tasks.":[114],"An":[115],"analysis":[116],"responses":[119],"highlights":[120],"distinctly":[121],"their":[122],"pros":[123],"cons.":[125],"Our":[126],"findings":[127],"suggest":[128],"achieving":[129],"not":[134],"intrinsically":[135],"obtained":[136],"by":[137],"LLMs,":[138],"future":[140],"should":[142],"focus":[143],"more":[144],"bridging":[146],"gap":[148],"between":[149],"improve":[155],"experience":[158],"for":[159],"musicians.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
