{"id":"https://openalex.org/W4412886727","doi":"https://doi.org/10.18653/v1/2025.acl-long.237","title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","display_name":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886727","doi":"https://doi.org/10.18653/v1/2025.acl-long.237"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.237","pdf_url":"https://aclanthology.org/2025.acl-long.237.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.237.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038862367","display_name":"Kuofeng Gao","orcid":"https://orcid.org/0000-0002-5667-8238"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuofeng Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034104790","display_name":"Shu\u2010Tao Xia","orcid":"https://orcid.org/0000-0002-8639-982X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu-Tao Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665814","display_name":"Ke Xu","orcid":"https://orcid.org/0000-0003-2587-8517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042899882","display_name":"Philip H. S. Torr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip Torr","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055994909","display_name":"Jindong Gu","orcid":"https://orcid.org/0009-0000-0574-0129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jindong Gu","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":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4763","last_page":"4784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9943000078201294,"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":0.9943000078201294,"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/T12031","display_name":"Speech and dialogue systems","score":0.987500011920929,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9657999873161316,"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/benchmarking","display_name":"Benchmarking","score":0.8463126420974731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519156336784363},{"id":"https://openalex.org/keywords/audio-equipment","display_name":"Audio equipment","score":0.42357444763183594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35378527641296387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34289872646331787},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32806363701820374},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0995822548866272}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8463126420974731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519156336784363},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.42357444763183594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35378527641296387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34289872646331787},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32806363701820374},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0995822548866272},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.237","pdf_url":"https://aclanthology.org/2025.acl-long.237.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.237","pdf_url":"https://aclanthology.org/2025.acl-long.237.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2802018518","display_name":null,"funder_award_id":"62171248","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886727.pdf","grobid_xml":"https://content.openalex.org/works/W4412886727.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2065933610"],"abstract_inverted_index":{"Large":[0],"Audio-Language":[1],"Models":[2],"(LALMs),":[3],"such":[4,157,172],"as":[5,158,173],"GPT-4o,":[6],"have":[7],"recently":[8],"unlocked":[9],"audio":[10,34,51,77,106,130,165],"dialogue":[11,52,78,166],"capabilities,":[12],"enabling":[13],"direct":[14],"spoken":[15],"exchanges":[16],"with":[17,121,149],"humans.The":[18],"potential":[19],"of":[20,29,46,70,94,102,117,135],"LALMs":[21,47,81,147],"broadens":[22],"their":[23],"applicability":[24],"across":[25],"a":[26,39],"wide":[27],"range":[28],"practical":[30],"scenarios":[31],"supported":[32],"by":[33],"dialogues.However,":[35],"given":[36],"these":[37],"advancements,":[38],"comprehensive":[40],"benchmark":[41,72,179],"to":[42],"evaluate":[43],"the":[44,49,75,100,113,133],"performance":[45],"in":[48,82,105],"open-ended":[50,76,129],"understanding":[53,154],"remains":[54],"absent":[55],"currently.To":[56],"address":[57],"this":[58],"gap,":[59],"we":[60,97],"propose":[61,99],"an":[62],"Audio":[63],"Dialogue":[64],"Understanding":[65],"Benchmark":[66],"(ADU-Bench),":[67],"which":[68],"consists":[69],"4":[71,92],"datasets.They":[73],"assess":[74],"ability":[79],"for":[80,132],"3":[83],"general":[84],"scenarios,":[85],"12":[86],"skills,":[87],"9":[88],"multilingual":[89],"languages,":[90,162],"and":[91,152,163,177],"categories":[93],"ambiguity":[95,103],"handling.Notably,":[96],"firstly":[98],"evaluation":[101],"handling":[104,164],"dialogues":[107,131],"that":[108,145],"expresses":[109],"different":[110,122,169],"intentions":[111],"beyond":[112],"same":[114],"literal":[115],"meaning":[116],"sentences,":[118],"e.g.,":[119],"\"Really!?\"":[120],"intonations.In":[123],"summary,":[124],"ADU-Bench":[125],"includes":[126],"over":[127],"20,000":[128],"assessment":[134],"LALMs.Through":[136],"extensive":[137],"experiments":[138],"on":[139],"16":[140],"LALMs,":[141],"our":[142],"analysis":[143],"reveals":[144],"existing":[146],"struggle":[148],"mathematical":[150],"symbols":[151],"formulas,":[153],"human":[155],"behavior":[156],"roleplay,":[159],"comprehending":[160],"multiple":[161],"ambiguities":[167],"from":[168],"phonetic":[170],"elements,":[171],"intonations,":[174],"pause":[175],"positions,":[176],"homophones.The":[178],"is":[180],"available":[181],"at":[182],"https://adu-bench.github.io/.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}