{"id":"https://openalex.org/W7214065699","doi":"https://doi.org/10.48550/arxiv.2609.26028","title":"REVE: Efficient Hallucination Correction for Large Audio-Language Models via Reused Encoder States","display_name":"REVE: Efficient Hallucination Correction for Large Audio-Language Models via Reused Encoder States","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214065699","doi":"https://doi.org/10.48550/arxiv.2609.26028"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.26028","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26028","pdf_url":"https://arxiv.org/pdf/2609.26028","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.26028","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102610011","display_name":"Hongjin Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song, Hongjin","raw_affiliation_strings":["Beijing Institute of Technology , Zhuhai , Guangdong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology , Zhuhai , Guangdong , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148861705","display_name":"Jiasheng Kuang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuang, Jiasheng","raw_affiliation_strings":["Beijing Institute of Technology , Zhuhai , Guangdong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology , Zhuhai , Guangdong , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152516880","display_name":"Xinyu Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Xinyu","raw_affiliation_strings":["Beijing Institute of Technology , Zhuhai , Guangdong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology , Zhuhai , Guangdong , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152541633","display_name":"Qiuyu Fang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang, Qiuyu","raw_affiliation_strings":["Beijing Institute of Technology , Zhuhai , Guangdong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology , Zhuhai , Guangdong , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101971236","display_name":"Ziyu Wu","orcid":"https://orcid.org/0009-0006-8190-7174","observed_orcids":["https://orcid.org/0009-0006-8190-7174"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Ziyu","raw_affiliation_strings":["Beijing Institute of Technology , Zhuhai , Guangdong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology , Zhuhai , Guangdong , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041019194","display_name":"\u8b5a\u570b\u92c8","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Guowu","raw_affiliation_strings":["Beijing Institute of Technology , Zhuhai , Guangdong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology , Zhuhai , Guangdong , China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152574631","display_name":"Xiang Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Xiang","raw_affiliation_strings":["Beijing Institute of Technology , Zhuhai , Guangdong , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology , Zhuhai , Guangdong , China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9911999702453613,"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":0.9911999702453613,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00559999980032444,"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/T10860","display_name":"Speech and Audio Processing","score":0.0013000000035390258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hallucination-correction","display_name":"hallucination correction","score":0.9649999737739563},{"id":"https://openalex.org/keywords/audio-language-models","display_name":"audio-language models","score":0.7139999866485596},{"id":"https://openalex.org/keywords/sound-event-detection","display_name":"sound event detection","score":0.7020000219345093},{"id":"https://openalex.org/keywords/audio-captioning","display_name":"audio captioning","score":0.47200000286102295},{"id":"https://openalex.org/keywords/audioset","display_name":"AudioSet","score":0.628000020980835}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.838100016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425000071525574},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5203999876976013},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3075000047683716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.26028","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26028","pdf_url":"https://arxiv.org/pdf/2609.26028","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.26028","doi":"https://doi.org/10.48550/arxiv.2609.26028","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.26028","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.26028","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.26028","pdf_url":"https://arxiv.org/pdf/2609.26028","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214065699.pdf","grobid_xml":"https://content.openalex.org/works/W7214065699.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161147884","https://openalex.org/W7148362664","https://openalex.org/W2889351461","https://openalex.org/W7212007318","https://openalex.org/W7118021772","https://openalex.org/W7147747775","https://openalex.org/W7128686409","https://openalex.org/W7129742916","https://openalex.org/W7214181873","https://openalex.org/W7133833858"],"abstract_inverted_index":{"Large":[0],"audio-language":[1],"models":[2],"may":[3],"mention":[4],"acoustic":[5],"events":[6],"that":[7,47],"are":[8],"absent":[9],"from":[10,69],"the":[11,53,87,131,145],"input.":[12],"A":[13],"separate":[14,32],"audio":[15,28,62,88],"event":[16,83],"detector":[17],"can":[18],"verify":[19,81],"these":[20],"mentions,":[21],"but":[22],"doing":[23],"so":[24],"requires":[25],"a":[26,31,44,99,114],"second":[27,109],"encoder":[29],"and":[30,107,121,139],"forward":[33],"pass.":[34],"We":[35],"propose":[36],"Reused":[37],"Encoder":[38],"States":[39],"for":[40],"Verifying":[41],"Events":[42],"(REVE),":[43],"lightweight":[45],"method":[46],"uses":[48,66],"states":[49,68],"already":[50],"computed":[51],"by":[52],"target":[54],"model.":[55],"One":[56],"readout":[57],"summarizes":[58],"class":[59],"scores":[60],"across":[61],"frames,":[63],"while":[64],"another":[65],"pooled":[67],"four":[70],"consecutive":[71],"frame":[72],"intervals.":[73],"Class-aware":[74],"score":[75],"fusion":[76],"combines":[77],"their":[78],"outputs":[79],"to":[80,117],"generated":[82],"mentions":[84,97],"without":[85],"encoding":[86],"again.":[89],"On":[90],"AudioSet,":[91],"REVE":[92,112],"removes":[93],"92.9%":[94],"of":[95,119,130,147],"label-unsupported":[96],"under":[98],"faithful-mention":[100],"recall":[101],"constraint.":[102],"With":[103],"fewer":[104],"added":[105],"parameters":[106],"no":[108],"audio-encoding":[110],"pass,":[111],"achieves":[113],"reduction":[115],"comparable":[116],"those":[118],"CED-Tiny":[120],"CED-Base.":[122],"Its":[123],"complete":[124],"verification":[125],"latency":[126],"is":[127],"about":[128],"1/18":[129],"CED-Base":[132],"path.":[133],"Results":[134],"on":[135],"controlled":[136],"DESED":[137],"mixtures":[138],"different":[140],"target-model":[141],"architectures":[142],"further":[143],"confirm":[144],"effectiveness":[146],"encoder-state":[148],"reuse.":[149]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-24T00:00:00"}
