{"id":"https://openalex.org/W7148362664","doi":"https://doi.org/10.1109/asru65441.2025.11434595","title":"Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding","display_name":"Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148362664","doi":"https://doi.org/10.1109/asru65441.2025.11434595"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112788374","display_name":"T. C. Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tzu-Wen Hsu","raw_affiliation_strings":["Purdue University,West Lafayette,United States"],"affiliations":[{"raw_affiliation_string":"Purdue University,West Lafayette,United States","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132820749","display_name":"Ke-Han Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ke-Han Lu","raw_affiliation_strings":["National Taiwan University Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071482462","display_name":"Cheng-Han Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Han Chiang","raw_affiliation_strings":["National Taiwan University Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132807525","display_name":"Hung-Yi Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112788374"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85851761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6862999796867371,"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":0.6862999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.06430000066757202,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.016599999740719795,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.9110000133514404},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7900000214576721},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6482999920845032},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6212999820709229},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4099000096321106},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.36570000648498535}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9110000133514404},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7900000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869000196456909},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6482999920845032},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922999978065491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5336999893188477},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35690000653266907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2776706361","wikidata":"https://www.wikidata.org/wiki/Q1054088","display_name":"Auditory hallucination","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W4313014461","https://openalex.org/W4385571645","https://openalex.org/W4391021627","https://openalex.org/W4392902623","https://openalex.org/W4402112110","https://openalex.org/W4402112183","https://openalex.org/W4404356490","https://openalex.org/W4404534210","https://openalex.org/W4408352589","https://openalex.org/W4408354168","https://openalex.org/W4411119642","https://openalex.org/W4415433526","https://openalex.org/W4415433917","https://openalex.org/W4416036756"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Audio-Language":[1],"Models":[2],"(LALMs)":[3],"can":[4,35,117],"take":[5],"audio":[6,72,86,123],"and":[7,12,69,100],"text":[8],"as":[9],"the":[10,16,41,45,64,71,79,85,105,119,142],"inputs":[11],"answer":[13],"questions":[14],"about":[15],"audio.":[17,42],"While":[18],"prior":[19],"LALMs":[20,34,99],"have":[21],"shown":[22],"strong":[23],"performance":[24],"on":[25,93,121],"standard":[26],"benchmarks,":[27],"there":[28],"has":[29],"been":[30],"alarming":[31],"evidence":[32],"that":[33,58,102,115],"hallucinate":[36],"what":[37],"is":[38,87],"presented":[39],"in":[40,147],"To":[43],"mitigate":[44],"hallucination":[46,95],"of":[47,144],"LALMs,":[48],"we":[49],"introduce":[50],"Audio-Aware":[51],"Decoding":[52],"(AAD),":[53],"a":[54],"lightweight":[55],"inference-time":[56],"strategy":[57],"uses":[59],"contrastive":[60,75],"decoding":[61],"to":[62,110,130,140],"compare":[63],"token":[65],"prediction":[66],"logits":[67],"with":[68,97],"without":[70],"context.":[73],"By":[74],"decoding,":[76],"AAD":[77,103,116],"promotes":[78],"tokens":[80],"whose":[81],"probability":[82],"increases":[83],"when":[84],"present.":[88],"We":[89,112,135],"conduct":[90,136],"our":[91],"experiment":[92],"object":[94],"datasets":[96,125],"three":[98],"show":[101,114],"improves":[104],"F1":[106],"score":[107],"by":[108,128],"0.046":[109],"0.428.":[111],"also":[113],"improve":[118],"accuracy":[120],"general":[122],"QA":[124],"like":[126],"Clotho-AQA":[127],"5.4%":[129],"$\\mathbf{1":[131],"0.":[132],"3":[133],"\\%}$.":[134],"thorough":[137],"ablation":[138],"studies":[139],"understand":[141],"effectiveness":[143],"each":[145],"component":[146],"AAD.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}