{"id":"https://openalex.org/W7166869784","doi":"https://doi.org/10.18653/v1/2026.findings-acl.439","title":"Speak No Evil, Just Prompt: Low-resource Multilingual Toxic Speech Detection with Audio Language Model","display_name":"Speak No Evil, Just Prompt: Low-resource Multilingual Toxic Speech Detection with Audio Language Model","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166869784","doi":"https://doi.org/10.18653/v1/2026.findings-acl.439"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.439","pdf_url":"https://aclanthology.org/2026.findings-acl.439.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.439.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116805924","display_name":"Mingzi Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingzi Zuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139817560","display_name":"Lei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735625","display_name":"Hailiang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hailiang Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139760783","display_name":"Shengzhi Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengzhi Huo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034211796","display_name":"Changyu Dong","orcid":"https://orcid.org/0000-0002-8625-0275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changyu Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139776697","display_name":"Xin Eric Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139808603","display_name":"Bo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139774494","display_name":"Hao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Liu","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":0.85852218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9039","last_page":"9053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.7749000191688538,"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":0.7749000191688538,"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":0.03920000046491623,"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":0.01759999990463257,"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/voice-activity-detection","display_name":"Voice activity detection","score":0.38019999861717224},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34389999508857727},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2939999997615814},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.289900004863739},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27149999141693115},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.27000001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165000200271606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48089998960494995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48030000925064087},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3993000090122223},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.38019999861717224},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.25780001282691956},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.439","pdf_url":"https://aclanthology.org/2026.findings-acl.439.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.439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.439","pdf_url":"https://aclanthology.org/2026.findings-acl.439.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44693523645401}],"awards":[{"id":"https://openalex.org/G6303818620","display_name":null,"funder_award_id":"518060","funder_id":"https://openalex.org/F4320325571","funder_display_name":"Shenzhen University"}],"funders":[{"id":"https://openalex.org/F4320325571","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166869784.pdf","grobid_xml":"https://content.openalex.org/works/W7166869784.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"widespread":[1],"dissemination":[2],"of":[3,61,94,144],"toxic":[4,95],"content":[5],"on":[6,31,80,86],"online":[7],"platforms":[8],"poses":[9],"a":[10,36,78,106,112,141],"critical":[11],"threat":[12],"to":[13,117],"user":[14],"experience.Toxicity":[15],"detection":[16,97,121],"in":[17,50,151],"speech":[18,41,69,96],"receives":[19],"significantly":[20],"less":[21],"research":[22],"attention":[23],"than":[24],"its":[25],"text":[26,45],"counterpart.Most":[27],"existing":[28],"methods":[29,153],"rely":[30],"high-resource":[32],"languages":[33,52,73,82],"and":[34,44,53,74,83,101,133,165],"employ":[35],"cascaded":[37],"pipeline":[38],"combining":[39],"automatic":[40],"recognition":[42],"(ASR)":[43],"classifiers.These":[46],"designs":[47],"limit":[48],"robustness":[49],"low-resource":[51,81],"discard":[54],"important":[55],"acoustic":[56],"cues.To":[57],"address":[58],"the":[59,66,90,147],"lack":[60],"datasets,":[62],"we":[63,88],"construct":[64],"PolySpeechTox,":[65,87,138],"first":[67,91],"toxicity-annotated":[68],"dataset":[70],"spanning":[71],"53":[72],"accent":[75],"varieties,":[76],"with":[77],"focus":[79],"multiple":[84],"accents.Based":[85],"conduct":[89],"systematic":[92],"study":[93],"under":[98],"low-resource,":[99],"multilingual,":[100],"multi-accent":[102],"conditions.We":[103],"propose":[104],"SoftPrompt-TSD,":[105],"prompt-based":[107],"adaptation":[108],"framework":[109],"that":[110],"leverages":[111],"frozen":[113],"audio":[114],"language":[115],"model":[116],"perform":[118],"end-to-end":[119],"toxicity":[120],"without":[122],"ASR.The":[123],"decomposed":[124],"soft-prompt":[125],"design":[126],"balances":[127],"global":[128],"task":[129],"alignment,":[130],"cross-lingual":[131],"generalization,":[132],"language-specific":[134],"or":[135],"accent-specific":[136],"calibration.On":[137],"SoftPrompt-TSD":[139,160],"achieves":[140],"micro-averaged":[142],"ROC-AUC":[143],"98.07%,":[145],"mitigating":[146],"severe":[148],"failures":[149],"observed":[150],"baseline":[152],"for":[154],"several":[155],"languages.In":[156],"three":[157],"generalization":[158,163],"experiments,":[159],"demonstrates":[161],"superior":[162],"capability":[164],"maintains":[166],"robust":[167],"performance":[168],"against":[169],"distribution":[170],"shifts.":[171]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}