{"id":"https://openalex.org/W7207758564","doi":"https://doi.org/10.48550/arxiv.2609.02000","title":"Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework","display_name":"Who Drives the Probability Game of VLMs? A Temporal Causal Drive Evaluation Framework","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7207758564","doi":"https://doi.org/10.48550/arxiv.2609.02000"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.02000","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02000","pdf_url":"https://arxiv.org/pdf/2609.02000","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.02000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139806058","display_name":"Shuyao Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Shuyao","raw_affiliation_strings":["College of Artificial Intelligence , Beijing Normal University","Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence , Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]},{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041386552","display_name":"Shengling Wang","orcid":"https://orcid.org/0000-0002-6698-3623","observed_orcids":["https://orcid.org/0000-0002-6698-3623"]},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Shengling","raw_affiliation_strings":["College of Artificial Intelligence , Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence , Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124939287","display_name":"Haoyu Niu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Niu, Haoyu","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121223985","display_name":"Ke Chao","orcid":"https://orcid.org/0009-0006-9096-3725","observed_orcids":["https://orcid.org/0009-0006-9096-3725"]},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao, Ke","raw_affiliation_strings":["College of Artificial Intelligence , Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence , Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149439832","display_name":"Changwei Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Changwei","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113017632","display_name":"Xinran Duan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duan, Xinran","raw_affiliation_strings":["College of Artificial Intelligence , Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence , Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148884815","display_name":"Chaoyong Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Chaoyong","raw_affiliation_strings":["College of Artificial Intelligence , Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence , Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0,"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":0.0,"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":0.9959999918937683},{"id":"https://openalex.org/keywords/structural-causal-models","display_name":"structural causal models","score":0.824999988079071},{"id":"https://openalex.org/keywords/autoregressive-decoding","display_name":"autoregressive decoding","score":0.7519999742507935},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.515999972820282},{"id":"https://openalex.org/keywords/backdoor-adjustment","display_name":"backdoor adjustment","score":0.8460000157356262},{"id":"https://openalex.org/keywords/multimodal-generation","display_name":"multimodal generation","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6258000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946000218391418},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5252000093460083},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32179999351501465},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C2987525970","wikidata":"https://www.wikidata.org/wiki/Q96374569","display_name":"Causal analysis","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.02000","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02000","pdf_url":"https://arxiv.org/pdf/2609.02000","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.02000","doi":"https://doi.org/10.48550/arxiv.2609.02000","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.02000","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:2609.02000","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.02000","pdf_url":"https://arxiv.org/pdf/2609.02000","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207758564.pdf","grobid_xml":"https://content.openalex.org/works/W7207758564.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223039758","https://openalex.org/W7211909313","https://openalex.org/W7162680334","https://openalex.org/W7165046792","https://openalex.org/W4414893770","https://openalex.org/W7131428648","https://openalex.org/W4405962609","https://openalex.org/W7127346143","https://openalex.org/W4416035473","https://openalex.org/W4415328886"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"are":[3],"increasingly":[4],"evaluated":[5],"on":[6,95,106,122],"complex":[7],"image":[8],"and":[9,20,36,50,65,81,100,116,130,141,153],"video":[10],"understanding":[11],"tasks,":[12],"yet":[13],"conventional":[14],"metrics":[15],"primarily":[16],"assess":[17],"final-answer":[18],"quality":[19],"reveal":[21,108],"little":[22],"about":[23],"how":[24],"different":[25],"information":[26],"sources":[27],"shape":[28],"the":[29,42,146],"generation":[30,88],"process.":[31],"We":[32],"propose":[33],"a":[34,58,109],"causal":[35],"temporal":[37],"evaluation":[38],"framework":[39],"that":[40,128,166],"traces":[41],"evolving":[43],"roles":[44],"of":[45],"visual":[46,117],"input,":[47],"question":[48,115],"text,":[49],"generated":[51,123],"prefixes":[52],"during":[53],"autoregressive":[54],"decoding.":[55],"Grounded":[56],"in":[57],"Structural":[59],"Causal":[60,74,78,83],"Model,":[61],"we":[62],"use":[63],"interventions":[64],"backdoor":[66],"adjustment":[67],"to":[68],"derive":[69],"three":[70],"step-indexed":[71],"causal-drive":[72,167],"metrics---Visual":[73],"Drive":[75,79,84],"(VCD),":[76],"Question":[77],"(QCD),":[80],"Prefix":[82],"(PCD)---for":[85],"characterizing":[86],"source-specific":[87],"patterns":[89],"without":[90],"requiring":[91],"reference":[92],"answers.":[93],"Experiments":[94],"Qwen3-VL-8B-Instruct":[96],"across":[97],"MAVIS,":[98],"LLaVA-Video-178K,":[99],"MiraData,":[101],"together":[102],"with":[103],"cross-model":[104],"validation":[105,126],"InternVL2-8B,":[107],"consistent":[110],"transition":[111],"from":[112,159],"stronger":[113],"early":[114],"guidance":[118],"toward":[119],"increasing":[120],"reliance":[121],"prefixes.":[124],"Randomized-intervention":[125],"shows":[127],"QCD":[129],"PCD":[131],"reduce":[132],"recovery":[133],"error":[134],"over":[135],"observational":[136],"PMI":[137],"baselines":[138],"by":[139],"34.8\\%":[140],"47.1\\%,":[142],"respectively.":[143],"On":[144],"VLMBias,":[145],"prefix--visual":[147],"imbalance":[148],"score":[149],"achieves":[150],"0.767":[151],"AUROC":[152],"0.873":[154],"AUPRC":[155],"for":[156,173],"distinguishing":[157],"prior-driven":[158],"visually":[160],"grounded":[161],"generations.":[162],"These":[163],"results":[164],"show":[165],"trajectories":[168],"provide":[169],"complementary":[170],"source-level":[171],"diagnostics":[172],"multimodal":[174],"generation.":[175]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-04T00:00:00"}