{"id":"https://openalex.org/W4415328840","doi":"https://doi.org/10.1109/wacv61042.2026.00459","title":"Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition","display_name":"Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4415328840","doi":"https://doi.org/10.1109/wacv61042.2026.00459"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15367","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120054753","display_name":"Dasol Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Dasol Choi","raw_affiliation_strings":["AIM Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIM Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120054754","display_name":"Seunghyun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seunghyun Lee","raw_affiliation_strings":["Yonsei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120054755","display_name":"Youngsook Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youngsook Song","raw_affiliation_strings":["Lablup Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lablup Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4724","last_page":"4732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9182999730110168,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9182999730110168,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reliability","display_name":"Reliability (semiconductor)","score":0.6789000034332275},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6151999831199646},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4943000078201294},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.444599986076355},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3522999882698059},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.34470000863075256},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.30889999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685699999332428},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6789000034332275},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6047000288963318},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4943000078201294},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C133112747","wikidata":"https://www.wikidata.org/wiki/Q7251931","display_name":"Protocol analysis","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2549999952316284}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.15367","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15367","pdf_url":"https://arxiv.org/pdf/2505.15367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15367","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15367","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15367","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15367","pdf_url":"https://arxiv.org/pdf/2505.15367","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415328840.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"shown":[4],"capabilities":[5],"in":[6,13,131,140],"interpreting":[7],"visual":[8,142],"content,":[9],"but":[10,50,88],"their":[11],"reliability":[12,130],"safety-critical":[14,132],"scenarios":[15,102],"remains":[16],"insufficiently":[17],"explored.":[18],"We":[19],"introduce":[20],"VERI,":[21],"a":[22,47,57],"diagnostic":[23],"benchmark":[24],"comprising":[25],"200":[26],"synthetic":[27,120],"images":[28,36],"(100":[29],"contrastive":[30],"pairs)":[31,38],"and":[32,63,74,121],"additional":[33],"50":[34],"real-world":[35,122],"(25":[37],"for":[39],"validation.":[40],"Each":[41],"emergency":[42,64],"scene":[43],"is":[44],"paired":[45],"with":[46],"visually":[48],"similar":[49],"safe":[51,96,101],"counterpart":[52],"through":[53],"human":[54],"verification.":[55],"Using":[56],"two-stage":[58],"evaluation":[59],"protocol":[60],"(risk":[61],"identification":[62],"response),":[65],"we":[66],"assess":[67],"17":[68],"VLMs":[69],"across":[70],"medical":[71],"emergencies,":[72],"accidents,":[73],"natural":[75],"disasters.":[76],"Our":[77],"analysis":[78],"reveals":[79],"an":[80],"\"overreaction":[81],"problem\":":[82],"models":[83],"achieve":[84],"high":[85],"recall":[86],"(70\u2013100%)":[87],"suffer":[89],"from":[90,113],"low":[91],"precision,":[92],"misclassifying":[93],"31\u201396%":[94],"of":[95,117],"situations":[97],"as":[98],"dangerous.":[99],"Seven":[100],"were":[103],"universally":[104],"misclassified":[105],"by":[106],"all":[107],"models.":[108],"This":[109],"\"better-safe-than-sorry\"":[110],"bias":[111],"stems":[112],"contextual":[114,138],"over-interpretation":[115],"(88\u201398%":[116],"errors).":[118],"Both":[119],"datasets":[123],"confirm":[124],"these":[125],"systematic":[126],"patterns,":[127],"challenging":[128],"VLM":[129],"applications.":[133],"Addressing":[134],"this":[135],"requires":[136],"enhanced":[137],"reasoning":[139],"ambiguous":[141],"situations.":[143]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-19T00:00:00"}