{"id":"https://openalex.org/W7214097204","doi":"https://doi.org/10.48550/arxiv.2609.25770","title":"Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs","display_name":"Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214097204","doi":"https://doi.org/10.48550/arxiv.2609.25770"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.25770","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25770","pdf_url":"https://arxiv.org/pdf/2609.25770","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/2609.25770","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037035833","display_name":"\u6797\u5b9a\u6837","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Dingyang","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152568947","display_name":"Yingfeng Luo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Yingfeng","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152570234","display_name":"Chenglong Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Chenglong","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124880332","display_name":"Chenwei Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Chenwei","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044361097","display_name":"Anxiang Ma","orcid":"https://orcid.org/0009-0007-4290-8171","observed_orcids":["https://orcid.org/0009-0007-4290-8171"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Anxiang","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124911404","display_name":"Jingbo Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Jingbo","raw_affiliation_strings":["NiuTrans Research , Shenyang , China","School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NiuTrans Research , Shenyang , China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129886799","display_name":"Tong Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Tong","raw_affiliation_strings":["NiuTrans Research , Shenyang , China","School of Computer Science and Engineering , Northeastern University , Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NiuTrans Research , Shenyang , China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":9.999999747378752e-05,"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/vision-language-models","display_name":"vision-language models","score":0.9909999966621399},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.8270000219345093},{"id":"https://openalex.org/keywords/image-resizing","display_name":"image scaling","score":0.7440000176429749},{"id":"https://openalex.org/keywords/image-tiling","display_name":"image tiling","score":0.7179999947547913},{"id":"https://openalex.org/keywords/configuration-changes","display_name":"configuration changes","score":0.5249999761581421},{"id":"https://openalex.org/keywords/llava-next","display_name":"LLaVA-NeXT","score":0.9369999766349792},{"id":"https://openalex.org/keywords/text-transcription","display_name":"textual transcription","score":0.5090000033378601}],"concepts":[{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068000197410583},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5584999918937683},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5432000160217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643999934196472},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2776058522","wikidata":"https://www.wikidata.org/wiki/Q2364768","display_name":"Visual field","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.25770","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25770","pdf_url":"https://arxiv.org/pdf/2609.25770","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.2609.25770","doi":"https://doi.org/10.48550/arxiv.2609.25770","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.25770","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.25770","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.25770","pdf_url":"https://arxiv.org/pdf/2609.25770","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/W7214097204.pdf","grobid_xml":"https://content.openalex.org/works/W7214097204.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415966298","https://openalex.org/W7163891676","https://openalex.org/W7154968747","https://openalex.org/W7167585410","https://openalex.org/W4416344032","https://openalex.org/W7214739966","https://openalex.org/W4415800735","https://openalex.org/W7153978741","https://openalex.org/W7215038371","https://openalex.org/W6966671024"],"abstract_inverted_index":{"Vision-language":[0],"models":[1,66,104,136],"(VLMs)":[2],"have":[3],"achieved":[4],"strong":[5],"performance":[6],"on":[7],"tasks":[8],"such":[9,31],"as":[10,32],"visual":[11,29],"question":[12,69],"answering,":[13],"yet":[14],"small":[15,49],"image":[16,33],"resizes":[17,50],"can":[18,72,92,133,140],"turn":[19],"correct":[20,76,120],"answers":[21],"into":[22],"errors.":[23],"We":[24,101],"investigate":[25],"whether":[26],"changes":[27,91,132],"in":[28,60,86],"configuration,":[30],"tiling":[34],"and":[35,45,108],"token":[36],"arrangement,":[37],"contribute":[38],"to":[39,81],"this":[40],"instability.":[41],"Across":[42],"seven":[43],"checkpoints":[44],"four":[46],"benchmarks,":[47],"equally":[48],"cause":[51],"more":[52],"correctness":[53],"flips":[54],"when":[55,78],"they":[56,139],"switch":[57],"configurations.":[58],"Surprisingly,":[59],"over":[61],"half":[62],"of":[63,96,117,122],"these":[64,115],"cases,":[65],"answer":[67,77],"the":[68,75,94],"incorrectly":[70],"but":[71],"still":[73,141],"read":[74],"told":[79],"what":[80],"read.":[82,142],"Furthermore,":[83],"attention":[84],"interventions":[85],"LLaVA-NeXT":[87],"suggest":[88],"that":[89,130],"configuration":[90,131],"weaken":[93],"use":[95,137],"readable":[97,125],"information":[98,138],"during":[99],"answering.":[100],"therefore":[102],"guide":[103],"using":[105],"field":[106],"cues":[107],"their":[109],"own":[110],"transcriptions.":[111],"With":[112],"annotation":[113],"assistance,":[114],"forms":[116],"guidance":[118],"together":[119],"97.2%":[121],"errors":[123],"with":[124],"information.":[126],"These":[127],"findings":[128],"show":[129],"affect":[134],"how":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-24T00:00:00"}
