{"id":"https://openalex.org/W7138282079","doi":"https://doi.org/10.1609/aaai.v40i38.40480","title":"Is Your (Reasoning) Multimodal Language Model Vulnerable Toward Distractions?","display_name":"Is Your (Reasoning) Multimodal Language Model Vulnerable Toward Distractions?","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138282079","doi":"https://doi.org/10.1609/aaai.v40i38.40480"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i38.40480","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40480","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40480/44441","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40480/44441","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129735245","display_name":"Ming Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680137","display_name":"Hao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678033","display_name":"Jindong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jindong Wang","raw_affiliation_strings":["William & Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"William & Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736206","display_name":"Liwen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liwen Wang","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110936166","display_name":"Jingchen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingchen Sun","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129714171","display_name":"Wensheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wensheng Zhang","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.26512917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"32087","last_page":"32095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9898999929428101,"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":0.9898999929428101,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.003000000026077032,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0007999999797903001,"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/robustness","display_name":"Robustness (evolution)","score":0.6589999794960022},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4122999906539917},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3716999888420105},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.366100013256073},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3382999897003174},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.32409998774528503},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.31619998812675476},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.31450000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775000095367432},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6589999794960022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44600000977516174},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32499998807907104},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C137176749","wikidata":"https://www.wikidata.org/wiki/Q4105337","display_name":"Psychological resilience","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i38.40480","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40480","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40480/44441","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/40480","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i38.40480","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40480","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40480/44441","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138282079.pdf","grobid_xml":"https://content.openalex.org/works/W7138282079.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"achieved":[4],"success":[5],"in":[6,55,98,118,175],"tasks":[7],"such":[8,157],"as":[9,31,158],"visual":[10,79,150],"question":[11,60],"answering,":[12],"yet":[13],"their":[14],"resilience":[15,165],"to":[16,102,112],"distractions":[17,22,54,76,86,143],"remains":[18],"underexplored.":[19],"Understanding":[20],"how":[21,85],"affect":[23],"VLMs'":[24],"performance":[25,147],"is":[26,123],"crucial":[27],"for":[28,52,172],"real-world":[29],"applications,":[30],"input":[32],"data":[33],"often":[34],"contains":[35],"noisy":[36],"or":[37],"irrelevant":[38],"content.":[39],"This":[40],"paper":[41],"assesses":[42],"the":[43,56,70,88,176],"robustness":[44,177],"of":[45,58,92,136,178],"VLMs\u2014including":[46],"general-purpose":[47],"models":[48,94,128],"and":[49,80],"those":[50],"specialized":[51],"reasoning\u2014against":[53],"context":[57],"science":[59],"answering.":[61],"We":[62,83,138],"introduce":[63],"I-ScienceQA,":[64],"a":[65,115,133],"new":[66],"benchmark":[67],"based":[68],"on":[69],"ScienceQA":[71],"dataset,":[72],"which":[73],"systematically":[74],"injects":[75],"into":[77],"both":[78],"textual":[81,99,142],"contexts.":[82],"evaluate":[84],"perturb":[87],"underlying":[89],"reasoning":[90,119],"processes":[91],"these":[93,162],"by":[95],"analyzing":[96],"changes":[97],"explanations":[100],"leading":[101],"answers.":[103],"Our":[104],"findings":[105],"show":[106],"that":[107,141],"most":[108],"VLMs":[109],"are":[110],"vulnerable":[111],"distractions,":[113],"with":[114],"noticeable":[116],"degradation":[117],"when":[120],"extraneous":[121],"content":[122],"present.":[124],"In":[125],"particular,":[126],"some":[127],"(including":[129],"GPT-o4":[130],"mini)":[131],"exhibit":[132],"higher":[134],"degree":[135],"robustness.":[137],"also":[139],"observe":[140],"generally":[144],"cause":[145],"greater":[146],"declines":[148],"than":[149],"distractions.":[151],"Finally,":[152],"we":[153],"explore":[154],"mitigation":[155],"strategies":[156,163],"prompt":[159],"engineering.":[160],"Although":[161],"improve":[164],"modestly,":[166],"our":[167],"analysis":[168],"highlights":[169],"considerable":[170],"room":[171],"further":[173],"improvement":[174],"VLMs.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}