{"id":"https://openalex.org/W7140095328","doi":"https://doi.org/10.18653/v1/2026.eacl-long.42","title":"A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models","display_name":"A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140095328","doi":"https://doi.org/10.18653/v1/2026.eacl-long.42"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.42","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.42","pdf_url":"https://aclanthology.org/2026.eacl-long.42.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.42.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Iwona Christop","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iwona Christop","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mateusz Czy\u017cnikiewicz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mateusz Czy\u017cnikiewicz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pawe\u0142 Sk\u00f3rzewski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Sk\u00f3rzewski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"\u0141ukasz Bondaruk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u0141ukasz Bondaruk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jakub Kubiak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakub Kubiak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Marcin Lewandowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcin Lewandowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Marek Kubis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marek Kubis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.39470925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"953","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.22789999842643738,"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/T12031","display_name":"Speech and dialogue systems","score":0.22789999842643738,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12460000067949295,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.07029999792575836,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3882000148296356},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2906000018119812},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.2635999917984009},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.2621000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698199987411499},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952999949455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48249998688697815},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.42","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.42","pdf_url":"https://aclanthology.org/2026.eacl-long.42.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.42","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.42","pdf_url":"https://aclanthology.org/2026.eacl-long.42.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140095328.pdf","grobid_xml":"https://content.openalex.org/works/W7140095328.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Iwona":[0],"Christop,":[1],"Mateusz":[2],"Czy\u017cnikiewicz,":[3],"Pawe\u0142":[4],"Sk\u00f3rzewski,":[5],"\u0141ukasz":[6],"Bondaruk,":[7],"Jakub":[8],"Kubiak,":[9],"Marcin":[10],"Lewandowski,":[11],"Marek":[12],"Kubis.":[13],"Proceedings":[14],"of":[15,19,23],"the":[16,20,24],"19th":[17],"Conference":[18],"European":[21],"Chapter":[22],"Association":[25],"for":[26],"Computational":[27],"Linguistics":[28],"(Volume":[29],"1:":[30],"Long":[31],"Papers).":[32],"2026.":[33]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}
