{"id":"https://openalex.org/W7214928221","doi":"https://doi.org/10.48550/arxiv.2609.37863","title":"It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them","display_name":"It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214928221","doi":"https://doi.org/10.48550/arxiv.2609.37863"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37863","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37863","pdf_url":"https://arxiv.org/pdf/2609.37863","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37863","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039599296","display_name":"Nagham Omar","orcid":"https://orcid.org/0000-0002-9670-885X","observed_orcids":["https://orcid.org/0000-0002-9670-885X"]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Omar, Nagham","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058189899","display_name":"Mahmoud Jabarin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jabarin, Mahmoud","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153571204","display_name":"Kinan Ibraheem","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ibraheem, Kinan","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002842866","display_name":"Lotem Peled-Cohen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Peled-Cohen, Lotem","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6610999703407288,"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":0.6610999703407288,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09700000286102295,"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/T10028","display_name":"Topic Modeling","score":0.052000001072883606,"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/vision-language-models","display_name":"vision-language models","score":0.9829999804496765},{"id":"https://openalex.org/keywords/figurative-language","display_name":"figurative language","score":0.593999981880188},{"id":"https://openalex.org/keywords/literal-meaning","display_name":"literal meaning","score":0.46399998664855957},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.3840000033378601},{"id":"https://openalex.org/keywords/substitutability","display_name":"substitutability","score":0.4790000021457672}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.7376999855041504},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.680899977684021},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5573999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5442000031471252},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4925999939441681},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3799000084400177},{"id":"https://openalex.org/C96024061","wikidata":"https://www.wikidata.org/wiki/Q473596","display_name":"Self-image","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C125045340","wikidata":"https://www.wikidata.org/wiki/Q6002224","display_name":"Image formation","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37863","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37863","pdf_url":"https://arxiv.org/pdf/2609.37863","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37863","doi":"https://doi.org/10.48550/arxiv.2609.37863","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37863","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37863","pdf_url":"https://arxiv.org/pdf/2609.37863","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214928221.pdf","grobid_xml":"https://content.openalex.org/works/W7214928221.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4384662964","https://openalex.org/W4391673253","https://openalex.org/W4403853618","https://openalex.org/W4404330874","https://openalex.org/W4407794264","https://openalex.org/W4415316405","https://openalex.org/W4416780398","https://openalex.org/W6947991961","https://openalex.org/W7077911270","https://openalex.org/W7166877503"],"related_works":["https://openalex.org/W7219155369","https://openalex.org/W7155043235","https://openalex.org/W7162574141","https://openalex.org/W4416035818","https://openalex.org/W7125974262","https://openalex.org/W4416034542","https://openalex.org/W7153978741","https://openalex.org/W7164200813","https://openalex.org/W7166573239","https://openalex.org/W7222978026"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"are":[3],"increasingly":[4],"used":[5],"in":[6,137,176,185,193],"place":[7],"of":[8,111,142,195,209],"human":[9,160],"annotators,":[10],"making":[11],"it":[12,96,212],"important":[13],"that":[14,145,180,188,202],"substitutability":[15,216],"tests":[16],"reflect":[17],"the":[18,28,58,68,74,94,125,130,134,143,148,153,165,177,182,186,210],"model":[19],"rather":[20],"than":[21,184],"incidental":[22],"evaluation":[23],"conditions.":[24],"We":[25,84],"introduce":[26],"MIST,":[27],"Misleading-Image":[29],"Stress":[30],"Test:":[31],"200":[32],"English":[33],"sentences,":[34],"each":[35,86],"built":[36],"around":[37],"a":[38,54,90,114,199,215,219,224],"phrase":[39],"readable":[40],"either":[41],"figuratively":[42],"or":[43,60,170],"literally":[44],"and":[45,98,113,122,156],"shown":[46],"with":[47,133,158],"an":[48,106,203],"aligned":[49,107,169],"image":[50,56,62,79,87,108,135,166,204],"depicting":[51,57],"its":[52],"reading,":[53],"misleading":[55,115],"opposite,":[59],"no":[61,78],"at":[63],"all.":[64],"The":[65,172],"guidelines":[66],"require":[67],"label":[69],"to":[70,88],"be":[71],"decided":[72],"from":[73],"sentence":[75],"alone,":[76],"so":[77,214],"should":[80],"change":[81],"any":[82],"answer.":[83],"expected":[85],"pull":[89],"judge's":[91],"labels":[92,112,144],"toward":[93,152],"sense":[95,154],"depicts,":[97],"neither":[99],"kind":[100],"did.":[101],"Across":[102],"thirteen":[103],"VLM":[104],"judges,":[105],"changed":[109],"20.5%":[110],"one":[116],"19.4%,":[117],"close":[118],"for":[119],"every":[120],"judge":[121,200],"both":[123],"above":[124],"11.6%":[126],"produced":[127],"by":[128],"deleting":[129],"ignore-the-image":[131],"instruction":[132],"left":[136],"place.":[138],"Yet":[139],"only":[140],"37%":[141],"differ":[146],"between":[147],"two":[149,211],"images":[150],"moved":[151],"shown,":[155],"agreement":[157],"our":[159],"annotators":[161],"is":[162,167,174,201,205],"unchanged":[163],"whether":[164],"absent,":[168],"misleading.":[171],"effect":[173],"smaller":[175],"seven":[178],"judges":[179],"pass":[181],"alt-test":[183],"six":[187],"never":[189],"do,":[190],"but":[191],"present":[192],"all":[194],"them:":[196],"what":[197],"moves":[198],"there,":[206],"not":[207],"which":[208],"is,":[213],"verdict":[217],"describes":[218],"configuration":[220],"as":[221,223],"much":[222],"model.":[225]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}