{"id":"https://openalex.org/W7140100017","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.80","title":"Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations","display_name":"Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140100017","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.80"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.80","pdf_url":"https://aclanthology.org/2026.findings-eacl.80.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: EACL 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.80.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sheng-Lun Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng-Lun Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yu-Ling Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Ling Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yen-Hua Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yen-Hua Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hen-Hsen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hen-Hsen Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Hsin-Hsi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin-Hsi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.3860618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1570","last_page":"1589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.24779999256134033,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.24779999256134033,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.08560000360012054,"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"}},{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.06759999692440033,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.6771000027656555},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3483999967575073},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.32499998807907104},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.3082999885082245},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.29100000858306885},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.2840000092983246}],"concepts":[{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5005000233650208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4936000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3483999967575073},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3082999885082245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29019999504089355},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.80","pdf_url":"https://aclanthology.org/2026.findings-eacl.80.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.80","pdf_url":"https://aclanthology.org/2026.findings-eacl.80.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4454644024372101,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140100017.pdf","grobid_xml":"https://content.openalex.org/works/W7140100017.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"the":[3,16,125],"first":[4],"systematic":[5],"investigation":[6],"of":[7,43],"speech":[8,44,94],"bias":[9],"in":[10,121],"multilingual":[11],"MLLMs.We":[12],"construct":[13],"and":[14,30,35,37,54,65,69,89,102,119],"release":[15],"BIASINEAR":[17],"dataset,":[18],"a":[19,113],"speech-augmented":[20],"benchmark":[21],"based":[22],"on":[23],"Global":[24],"MMLU":[25],"Lite,":[26],"spanning":[27],"English,":[28],"Chinese,":[29],"Korean,":[31],"balanced":[32],"by":[33],"gender":[34],"accent,":[36],"totaling":[38],"70.8":[39],"hours":[40],"(4,249":[41],"minutes)":[42],"with":[45],"11,200":[46],"questions.Using":[47],"four":[48],"complementary":[49],"metrics":[50],"(accuracy,":[51],"entropy,":[52],"APES,":[53],"Fleiss'":[55],"),":[56],"we":[57],"evaluate":[58],"nine":[59],"representative":[60],"models":[61],"under":[62],"linguistic":[63],"(language":[64],"accent),":[66],"demographic":[67,82],"(gender),":[68],"structural":[70,98],"(option":[71],"order)":[72],"perturbations.Our":[73],"findings":[74],"reveal":[75],"that":[76,93],"MLLMs":[77],"are":[78],"relatively":[79],"robust":[80],"to":[81,87],"factors":[83],"but":[84],"highly":[85],"sensitive":[86],"language":[88],"option":[90],"order,":[91],"suggesting":[92],"can":[95,132],"amplify":[96],"existing":[97],"biases.Moreover,":[99],"architectural":[100],"design":[101],"reasoning":[103],"strategy":[104],"substantially":[105],"affect":[106],"robustness":[107,120],"across":[108],"languages.Overall,":[109],"this":[110],"study":[111],"establishes":[112],"unified":[114],"framework":[115],"for":[116],"assessing":[117],"fairness":[118],"speech-integrated":[122],"LLMs,":[123],"bridging":[124],"gap":[126],"between":[127],"text-and":[128],"speech-based":[129],"evaluation.The":[130],"resources":[131],"be":[133],"found":[134],"at":[135],"https://github.com/ntunlplab/BiasInEar":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-06T00:00:00"}