{"id":"https://openalex.org/W7140109573","doi":"https://doi.org/10.18653/v1/2026.eacl-short.18","title":"Task-Level Instructions Induction for Audio Question Answering from Few Examples","display_name":"Task-Level Instructions Induction for Audio Question Answering from Few Examples","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140109573","doi":"https://doi.org/10.18653/v1/2026.eacl-short.18"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-short.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-short.18","pdf_url":"https://aclanthology.org/2026.eacl-short.18.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-short.18.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130330735","display_name":"Po-Chun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Po-Chun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130340543","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":"https://openalex.org/A5130343785","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":3,"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":0.39681378,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5217999815940857,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.5217999815940857,"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/T11309","display_name":"Music and Audio Processing","score":0.18129999935626984,"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":0.09009999781847,"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/question-answering","display_name":"Question answering","score":0.6353999972343445},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26910001039505005},{"id":"https://openalex.org/keywords/questions-and-answers","display_name":"Questions and answers","score":0.2522999942302704},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.2522999942302704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589999794960022},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6353999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4772000014781952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-short.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-short.18","pdf_url":"https://aclanthology.org/2026.eacl-short.18.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-short.18","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-short.18","pdf_url":"https://aclanthology.org/2026.eacl-short.18.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5219195485115051}],"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/W7140109573.pdf","grobid_xml":"https://content.openalex.org/works/W7140109573.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"audio-language":[1],"models":[2,51],"(LALMs)":[3],"benefit":[4],"from":[5,77],"Chain-of-Thought":[6],"(CoT)":[7],"prompting":[8,41,56,99],"for":[9],"audio":[10,16,65,79],"question":[11],"answering":[12],"(AQA),":[13],"but":[14],"acquiring":[15],"CoT":[17],"examples":[18,80],"is":[19],"particularly":[20],"challenging":[21],"as":[22],"it":[23],"requires":[24],"sequential":[25],"listening":[26],"and":[27,32],"careful":[28],"integration":[29],"of":[30],"acoustic":[31],"linguistic":[33],"information.Surprisingly,":[34],"our":[35],"experiments":[36],"reveal":[37],"that":[38],"standard":[39],"few-shot":[40,55],"yields":[42],"inconsistent":[43],"results":[44],"compared":[45],"to":[46],"zero-shot":[47],"CoT,":[48],"with":[49],"several":[50],"showing":[52],"degraded":[53],"accuracy.Moreover,":[54],"incurs":[57],"substantially":[58],"higher":[59],"inference":[60,104],"costs":[61],"by":[62],"processing":[63],"multiple":[64],"demonstrations":[66,87],"per":[67,82],"inference.We":[68],"propose":[69],"Audio-Induct,":[70],"which":[71],"induces":[72],"reusable":[73],"textual":[74],"task":[75],"instructions":[76],"few":[78],"once":[81],"task,":[83],"requiring":[84],"no":[85],"additional":[86],"at":[88],"inference.Evaluated":[89],"on":[90],"9":[91],"LALMs":[92],"across":[93,110],"two":[94],"benchmarks,":[95],"Audio-Induct":[96],"outperforms":[97],"state-of-the-art":[98],"methods":[100],"while":[101],"maintaining":[102],"low":[103],"costs.Inducted":[105],"Task":[106],"Instructions":[107],"transfer":[108],"effectively":[109],"models,":[111],"enabling":[112],"scalable":[113],"deployment.":[114]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}