{"id":"https://openalex.org/W7166837620","doi":"https://doi.org/10.18653/v1/2026.acl-long.490","title":"Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images","display_name":"Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166837620","doi":"https://doi.org/10.18653/v1/2026.acl-long.490"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.490","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.490","pdf_url":"https://aclanthology.org/2026.acl-long.490.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.490.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128664513","display_name":"Qishun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qishun Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838443","display_name":"Shu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139830289","display_name":"Lijie Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lijie Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139819368","display_name":"Di Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Wang","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":0.83757809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10698","last_page":"10718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14074","display_name":"Persona Design and Applications","score":0.9595999717712402,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T14074","display_name":"Persona Design and Applications","score":0.9595999717712402,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10803","display_name":"Innovative Human-Technology Interaction","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3544999957084656},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3197999894618988},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.30379998683929443},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2842000126838684},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2775999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5809000134468079},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48980000615119934},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.490","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.490","pdf_url":"https://aclanthology.org/2026.acl-long.490.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.490","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.490","pdf_url":"https://aclanthology.org/2026.acl-long.490.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4795079661","display_name":null,"funder_award_id":"BAS/1/1689-01-01","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"},{"id":"https://openalex.org/F4320325295","display_name":"Zayed University","ror":"https://ror.org/03snqfa66"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166837620.pdf","grobid_xml":"https://content.openalex.org/works/W7166837620.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3,59,79],"(MLLMs)":[4],"face":[5],"safety":[6,20,34,71,95],"misalignment,":[7,50],"where":[8],"visual":[9,42,77,123],"inputs":[10],"enable":[11],"harmful":[12],"outputs.To":[13],"address":[14],"this,":[15],"existing":[16],"methods":[17],"require":[18],"explicit":[19],"labels":[21],"or":[22],"contrastive":[23],"data;":[24],"yet,":[25],"threat-related":[26,67,76],"concepts":[27],"are":[28,38],"concrete":[29],"and":[30,40,86,94,108],"visually":[31],"depictable,":[32],"while":[33,111],"concepts,":[35],"like":[36],"helpfulness,":[37],"abstract":[39],"lack":[41],"referents.Inspired":[43],"by":[44],"the":[45,81,101,117],"Self-Fulfilling":[46,54],"mechanism":[47,119],"underlying":[48],"emergent":[49],"we":[51],"propose":[52],"Visual":[53],"Alignment":[55],"(VSFA).VSFA":[56],"fine-tunes":[57],"vision-language":[58],"(VLMs)":[60],"on":[61],"neutral":[62],"VQA":[63],"tasks":[64],"constructed":[65],"around":[66],"images,":[68],"without":[69],"any":[70],"labels.Through":[72],"repeated":[73],"exposure":[74],"to":[75,122,129],"content,":[78],"internalize":[80],"implicit":[82],"semantics":[83],"of":[84],"vigilance":[85],"caution,":[87],"shaping":[88],"safetyoriented":[89],"personas.Experiments":[90],"across":[91],"multiple":[92],"VLMs":[93,130],"benchmarks":[96],"demonstrate":[97],"that":[98],"VSFA":[99],"reduces":[100],"attack":[102],"success":[103],"rate,":[104],"improves":[105],"response":[106],"quality,":[107],"mitigates":[109],"over-refusal":[110],"preserving":[112],"general":[113],"capabilities.Our":[114],"work":[115],"extends":[116],"self-fulfilling":[118],"from":[120],"text":[121],"modalities,":[124],"offering":[125],"a":[126],"label-free":[127],"approach":[128],"alignment.Code":[131],"is":[132],"available":[133],"at":[134],"https://github.":[135],"com/qazwsx123456123/VSFA.":[136]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
