{"id":"https://openalex.org/W4415100157","doi":"https://doi.org/10.48550/arxiv.2502.18008","title":"NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms","display_name":"NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms","publication_year":2025,"publication_date":"2025-02-25","ids":{"openalex":"https://openalex.org/W4415100157","doi":"https://doi.org/10.48550/arxiv.2502.18008"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.18008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.18008","pdf_url":"https://arxiv.org/pdf/2502.18008","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.18008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083052094","display_name":"Yashan Wang","orcid":"https://orcid.org/0000-0003-3379-1999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yashan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078252194","display_name":"Shangda Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shangda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101728295","display_name":"Junru Hu","orcid":"https://orcid.org/0000-0002-4335-1746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Jianhuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Xingjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Peng, Yueqi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yueqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072520198","display_name":"Yongxin Huang","orcid":"https://orcid.org/0000-0003-2892-5382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yongxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101598386","display_name":"Shuai Fan","orcid":"https://orcid.org/0000-0002-8593-9329"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012356492","display_name":"Xiaobing Li","orcid":"https://orcid.org/0000-0003-0113-824X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaobing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049175891","display_name":"Feng Yu","orcid":"https://orcid.org/0009-0007-0607-7315"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Maosong","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":false,"cited_by_count":1,"citation_normalized_percentile":null,"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":0.9484999775886536,"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":0.9484999775886536,"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":0.9460999965667725,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/musicality","display_name":"Musicality","score":0.5419999957084656},{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.5303000211715698},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4636000096797943},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.40799999237060547},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4025999903678894},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.40049999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6345000267028809},{"id":"https://openalex.org/C113194728","wikidata":"https://www.wikidata.org/wiki/Q4130159","display_name":"Musicality","level":3,"score":0.5419999957084656},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46959999203681946},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.397599995136261},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C146902061","wikidata":"https://www.wikidata.org/wiki/Q476590","display_name":"Music psychology","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.18008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.18008","pdf_url":"https://arxiv.org/pdf/2502.18008","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.18008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.18008","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.18008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.18008","pdf_url":"https://arxiv.org/pdf/2502.18008","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"NotaGen,":[2],"a":[3],"symbolic":[4,98,126],"music":[5,51,99,127],"generation":[6,79,100],"model":[7],"aiming":[8],"to":[9,38],"explore":[10],"the":[11,21,40,73,93],"potential":[12],"of":[13,23,50,95],"producing":[14],"high-quality":[15,61],"classical":[16,62],"sheet":[17],"music.":[18],"Inspired":[19],"by":[20],"success":[22],"Large":[24],"Language":[25],"Models":[26],"(LLMs),":[27],"NotaGen":[28,114],"adopts":[29],"pre-training,":[30],"fine-tuning,":[31],"and":[32,55,81,105],"reinforcement":[33,69],"learning":[34],"paradigms":[35],"(henceforth":[36],"referred":[37],"as":[39],"LLM":[41],"training":[42],"paradigms).":[43],"It":[44],"is":[45],"pre-trained":[46],"on":[47,58,65],"1.6M":[48],"pieces":[49],"in":[52,97,125],"ABC":[53],"notation,":[54],"then":[56],"fine-tuned":[57],"approximately":[59],"9K":[60],"compositions":[63],"conditioned":[64],"\"period-composer-instrumentation\"":[66],"prompts.":[67],"For":[68],"learning,":[70],"we":[71],"propose":[72],"CLaMP-DPO":[74,96],"method,":[75],"which":[76],"further":[77],"enhances":[78],"quality":[80],"controllability":[82],"without":[83],"requiring":[84],"human":[85,119],"annotations":[86],"or":[87],"predefined":[88],"rewards.":[89],"Our":[90],"experiments":[91],"demonstrate":[92],"efficacy":[94],"models":[101,117],"with":[102],"different":[103],"architectures":[104],"encoding":[106],"schemes.":[107],"Furthermore,":[108],"subjective":[109],"A/B":[110],"tests":[111],"show":[112],"that":[113],"outperforms":[115],"baseline":[116],"against":[118],"compositions,":[120],"greatly":[121],"advancing":[122],"musical":[123],"aesthetics":[124],"generation.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-13T00:00:00"}