{"id":"https://openalex.org/W7166846352","doi":"https://doi.org/10.18653/v1/2026.findings-acl.976","title":"Pardon? Evaluating Conversational Repair in Large Audio-Language Models","display_name":"Pardon? Evaluating Conversational Repair in Large Audio-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166846352","doi":"https://doi.org/10.18653/v1/2026.findings-acl.976"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.976","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.976","pdf_url":"https://aclanthology.org/2026.findings-acl.976.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.976.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029688755","display_name":"Shuanghong Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuanghong Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139715325","display_name":"Jinlei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinlei Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077555697","display_name":"Youchao Zhou","orcid":"https://orcid.org/0009-0005-3563-5625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youchao Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123506832","display_name":"Yanghao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanghao Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139790688","display_name":"Xuan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139788914","display_name":"Chong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139808221","display_name":"Wenxuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Zhang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83607299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19528","last_page":"19541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.1665000021457672,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.1665000021457672,"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/T12031","display_name":"Speech and dialogue systems","score":0.08179999887943268,"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":0.06729999929666519,"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/feature","display_name":"Feature (linguistics)","score":0.2680000066757202},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.267300009727478},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2605000138282776},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2529999911785126},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2410999983549118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5827000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36739999055862427},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2468000054359436},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2410999983549118},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23989999294281006}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.976","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.976","pdf_url":"https://aclanthology.org/2026.findings-acl.976.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.976","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.976","pdf_url":"https://aclanthology.org/2026.findings-acl.976.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166846352.pdf","grobid_xml":"https://content.openalex.org/works/W7166846352.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Audio-Language":[1],"Models":[2],"(LALMs)":[3],"have":[4],"demonstrated":[5],"strong":[6],"performance":[7],"in":[8,41],"spoken":[9,31,116],"question":[10],"answering":[11],"(QA),":[12],"with":[13],"existing":[14],"evaluations":[15,27],"primarily":[16],"focusing":[17],"on":[18,85,114],"answer":[19,127],"accuracy":[20,128],"and":[21,62,75,93,108,129,147,161,173,178],"robustness":[22],"to":[23,143],"acoustic":[24],"perturbations.However,":[25],"such":[26],"implicitly":[28],"assume":[29],"that":[30,38,57,100,165],"inputs":[32,138,168],"remain":[33],"semantically":[34],"answerable,":[35,140],"an":[36],"assumption":[37],"often":[39],"fails":[40],"real-world":[42],"interaction":[43],"when":[44,137],"essential":[45],"information":[46],"is":[47],"missing.In":[48],"this":[49,86],"work,":[50],"we":[51,88],"introduce":[52],"a":[53,69,81,97,123,154],"repair-aware":[54],"evaluation":[55,78,159],"setting":[56],"explicitly":[58],"distinguishes":[59],"between":[60,126],"answerable":[61,106],"unanswerable":[63,112,167],"audio":[64],"inputs.We":[65],"define":[66],"answerability":[67],"as":[68,169],"property":[70],"of":[71,156],"the":[72,90],"input":[73],"itself":[74],"construct":[76],"paired":[77],"conditions":[79,107],"using":[80],"semantic-acoustic":[82],"masking":[83],"protocol.Based":[84],"setting,":[87],"propose":[89],"Evaluability":[91],"Awareness":[92],"Repair":[94],"(EAR)":[95],"score,":[96],"non-compensatory":[98],"metric":[99],"jointly":[101],"evaluates":[102],"task":[103],"competence":[104],"under":[105,111],"repair":[109,172],"behavior":[110],"conditions.Experiments":[113],"two":[115],"QA":[117],"benchmarks":[118],"across":[119],"diverse":[120],"LALMs":[121],"reveal":[122],"consistent":[124],"gap":[125],"conversational":[130,150],"reliability:":[131],"while":[132],"many":[133],"models":[134],"perform":[135],"well":[136],"are":[139,180],"most":[141],"fail":[142],"recognize":[144],"semantic":[145],"unanswerability":[146],"initiate":[148],"appropriate":[149],"repair.These":[151],"findings":[152],"expose":[153],"limitation":[155],"prevailing":[157],"accuracy-centric":[158],"practices":[160],"motivate":[162],"reliability":[163],"assessments":[164],"treat":[166],"cues":[170],"for":[171],"continued":[174],"interaction.The":[175],"core":[176],"code":[177],"dataset":[179],"publicly":[181],"available":[182],"at":[183]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}