{"id":"https://openalex.org/W7140082374","doi":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9","title":"HumMusQA: A Human-written Music Understanding QA Benchmark Dataset","display_name":"HumMusQA: A Human-written Music Understanding QA Benchmark Dataset","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140082374","doi":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.nlp4musa-1.9","doi":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9","pdf_url":"https://aclanthology.org/2026.nlp4musa-1.9.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 4th Workshop on NLP for Music and Audio (NLP4MusA 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.nlp4musa-1.9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038446032","display_name":"Benno Weck","orcid":"https://orcid.org/0000-0002-5760-6922","observed_orcids":["https://orcid.org/0000-0002-5760-6922"]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Benno Weck","raw_affiliation_strings":["Universitat Pompeu Fabra"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070213058","display_name":"Pablo Puentes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123044942","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94","country_code":"ES","type":"education","lineage":["https://openalex.org/I123044942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Puentes","raw_affiliation_strings":["Universitat Aut\u00f2noma de Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Aut\u00f2noma de Barcelona","institution_ids":["https://openalex.org/I123044942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125666096","display_name":"Andrea Poltronieri","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Andrea Poltronieri","raw_affiliation_strings":["Universitat Pompeu Fabra"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130353793","display_name":"Satyajeet Prabhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Satyajeet Prabhu","raw_affiliation_strings":["Universitat Pompeu Fabra"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004451369","display_name":"Dmitry Bogdanov","orcid":"https://orcid.org/0000-0002-9469-0633","observed_orcids":["https://orcid.org/0000-0002-9469-0633"]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dmitry Bogdanov","raw_affiliation_strings":["Universitat Pompeu Fabra"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13909844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8988999724388123,"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":0.8988999724388123,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08879999816417694,"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":0.004900000058114529,"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/musical-understanding","display_name":"musical understanding","score":0.9860000014305115},{"id":"https://openalex.org/keywords/large-audio-language-models","display_name":"large audio language models","score":0.9359999895095825},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.7620000243186951},{"id":"https://openalex.org/keywords/listening-comprehension","display_name":"listening comprehension","score":0.5370000004768372},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6541000008583069},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4706000089645386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2370000034570694}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.nlp4musa-1.9","doi":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9","pdf_url":"https://aclanthology.org/2026.nlp4musa-1.9.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 4th Workshop on NLP for Music and Audio (NLP4MusA 2026)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.27877","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.27877","pdf_url":"https://arxiv.org/pdf/2603.27877","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2603.27877","doi":"https://doi.org/10.48550/arxiv.2603.27877","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.27877","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.nlp4musa-1.9","doi":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.nlp4musa-1.9","pdf_url":"https://aclanthology.org/2026.nlp4musa-1.9.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 4th Workshop on NLP for Music and Audio (NLP4MusA 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140082374.pdf","grobid_xml":"https://content.openalex.org/works/W7140082374.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7105006177","https://openalex.org/W4318351475","https://openalex.org/W7221773218","https://openalex.org/W6930525032","https://openalex.org/W4402670458","https://openalex.org/W7154265921","https://openalex.org/W4414699785","https://openalex.org/W7106673227","https://openalex.org/W4416057713","https://openalex.org/W7167678751"],"abstract_inverted_index":{"The":[0],"evaluation":[1],"of":[2,48,76],"music":[3,42],"understanding":[4],"in":[5],"Large":[6],"Audio-Language":[7],"Models":[8],"(LALMs)":[9],"requires":[10],"a":[11,25,37,45],"rigorously":[12],"defined":[13],"benchmark":[14,80],"that":[15,27,61],"truly":[16],"tests":[17],"whether":[18],"models":[19],"can":[20],"perceive":[21],"and":[22,53,84],"interpret":[23],"music,":[24],"standard":[26],"current":[28],"data":[29],"methodologies":[30],"frequently":[31],"fail":[32],"to":[33,41,89],"meet.This":[34],"paper":[35],"introduces":[36],"meticulously":[38],"structured":[39],"approach":[40],"evaluation,":[43],"proposing":[44],"new":[46],"dataset":[47],"320":[49],"handwritten":[50],"questions":[51],"curated":[52],"validated":[54],"by":[55],"experts":[56],"with":[57],"musical":[58],"training,":[59],"arguing":[60],"such":[62],"focused,":[63],"manual":[64],"curation":[65],"is":[66],"superior":[67],"for":[68],"probing":[69],"complex":[70],"audio":[71],"comprehension.To":[72],"demonstrate":[73],"the":[74,77],"use":[75],"dataset,":[78],"we":[79],"six":[81],"state-of-the-art":[82],"LALMs":[83],"additionally":[85],"test":[86],"their":[87],"robustness":[88],"uni-modal":[90],"shortcuts.":[91]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}